myGAMM4Bin <- function(dv,iv,cv,nv,dat)
{
indv <- paste(iv, collapse=" + ")
cova <- paste(cv, collapse=" + ")
if(length(nv)>1){
nstv <- paste("~","(","1","|",nv[1],"/",nv[2],")",sep="")
} else {
nstv <- paste("~","(","1","|",nv[1],")",sep="")
}
datnames <- names(dat)
if(iv %in% datnames) {
form1 <- paste(dv," ~ ",indv," + ",cova,sep="")
} else { form1 <- paste(dv," ~ ",cova,sep="")}
# print(form1)
# print(nstv)
mygam <- gamm4(as.formula(form1), family=binomial, random = as.formula(nstv), data = dat)
return(mygam)
}
mydir <- paste0("/Users/mpaulus/Dropbox (Personal)/Private/RDataAnalysis/ABCD_Data/Media/")
# File components:
myfile <- c("ABCD_")
datatext <-("SMA_CBCL_COG_ENV_")
GFAtext <- c("R_GFA_")
dateext <- c("09.02.2018")
myall <- paste(mydir,myfile,datatext,GFAtext,dateext,".RData",sep="")
load(myall)
mynames <- names(abcdnegreinf)
# Load different variable sets:
myall <- paste(mydir,"abcd_activars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_cbclvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_cogvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_friendvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_medvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_sulcvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_thickvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_volvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_screenvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_socialsummaryvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_physvars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_covars_08.23.2018",".RData",sep="")
load(myall)
myall <- paste(mydir,"abcd_suicidvars_08.23.2018",".RData",sep="")
load(myall)
# Assigns a temporary data set for computational purposes:
currdata <- abcdnegreinf
# Rename kids suicide variables:
kidsuicidevars <- suicidvars[intersect(grep("_t",suicidvars),grep("ksads",suicidvars))]
kidsuicidelabels <- c("selfinjurious_now","selfinjurious_past","wishdead_now","wishdead_past",
"SI_present","SI_past","suicideattempt_now","suicideattempt_past",
"selfinjurytodie_now","selfinjurythought_now","suicidethoughtmethod_now",
"suicideintent_now","suicideplan_now","suicideprep_now","suicideabort_now",
"suicidemethod_now","suicideattempt_now","selfinjurytodie_past",
"selfinjurythought_past","suicidethoughtmethod_past","suicideintent_past",
"suicideplan_past","suicideprep_past","suicideabort_past",
"suicidenumber_past","suicidemethod_past","suicideattempt_past")
# Rename the variables:
setnames(currdata, old=c(kidsuicidevars), new=c(kidsuicidelabels))
# Rename parents suicide variables:
parsuicidevars <- suicidvars[intersect(grep("_p",suicidvars),grep("ksads",suicidvars))]
parsuicidevars <- parsuicidevars[-c(1:4)]
parentsuicidelabels <- c("p_suicideAttempt_now","p_suicideAttempt_past","p_selfinjury_now","p_selfinjury_past","p_SImethod_now","p_suicideintent_now","p_suicidePlan_now","p_suicidePrep_now","p_suicudeInterrupt_now","p_suicidemethod_now","p_suicideTought_now","p_selfinjuryDeath_past","p_selfinjuryThought_past","p_SImethod_past","p_suicideintent_past","p_suicidePlan_past","p_suicidePrep_past","p_suicideInterrupt_past","p_numSA_past","p_Samethod_past","p_expectToDie_past")
homicidallabels <- c("p_homicidaldeas_now","p_homicidaldeas_poast","p_homicidalPlan_now","p_homicidalPlan_past")
# Rename the variables:
setnames(currdata, old=c(parsuicidevars), new=c(parentsuicidelabels))
kidsuicidetotal <- rowSums(currdata[,kidsuicidelabels])
parsuicidetotal <- rowSums(currdata[,parentsuicidelabels])
currdata$kidsitotal <- c(kidsuicidetotal)
currdata$parsitotal <- c(parsuicidetotal)
# Create a binary variable
currdata$KidsSIyes <- ifelse(currdata$kidsitotal>0,1,0)
currdata$ParSIyes <- ifelse(currdata$parsitotal>0,1,0)
currdata$KidsSIyes <- as.factor(currdata$KidsSIyes)
currdata$ParSIyes <- as.factor(currdata$ParSIyes)
# Describe and characterize the total variables
# individual kids items:
factordata <- data.frame(lapply(currdata[,kidsuicidelabels], factor))
describe(factordata[,kidsuicidelabels])
## factordata[, kidsuicidelabels]
##
## 27 Variables 4524 Observations
## ---------------------------------------------------------------------------
## selfinjurious_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4341 130
## Proportion 0.971 0.029
## ---------------------------------------------------------------------------
## selfinjurious_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4249 222
## Proportion 0.95 0.05
## ---------------------------------------------------------------------------
## wishdead_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4415 56
## Proportion 0.987 0.013
## ---------------------------------------------------------------------------
## wishdead_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4170 301
## Proportion 0.933 0.067
## ---------------------------------------------------------------------------
## SI_present
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4400 71
## Proportion 0.984 0.016
## ---------------------------------------------------------------------------
## SI_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4315 156
## Proportion 0.965 0.035
## ---------------------------------------------------------------------------
## suicideattempt_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4464 7
## Proportion 0.998 0.002
## ---------------------------------------------------------------------------
## suicideattempt_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4443 28
## Proportion 0.994 0.006
## ---------------------------------------------------------------------------
## selfinjurytodie_now
## n missing distinct value
## 4471 53 1 0
##
## Value 0
## Frequency 4471
## Proportion 1
## ---------------------------------------------------------------------------
## selfinjurythought_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4470 1
## Proportion 1 0
## ---------------------------------------------------------------------------
## suicidethoughtmethod_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4447 24
## Proportion 0.995 0.005
## ---------------------------------------------------------------------------
## suicideintent_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4459 12
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## suicideplan_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4459 12
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## suicideprep_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4462 9
## Proportion 0.998 0.002
## ---------------------------------------------------------------------------
## suicideabort_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4458 13
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## suicidemethod_now
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4451 20
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## suicideattempt_now.1
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4464 7
## Proportion 0.998 0.002
## ---------------------------------------------------------------------------
## selfinjurytodie_past
## n missing distinct value
## 4471 53 1 0
##
## Value 0
## Frequency 4471
## Proportion 1
## ---------------------------------------------------------------------------
## selfinjurythought_past
## n missing distinct value
## 4471 53 1 0
##
## Value 0
## Frequency 4471
## Proportion 1
## ---------------------------------------------------------------------------
## suicidethoughtmethod_past
## n missing distinct value
## 4471 53 1 0
##
## Value 0
## Frequency 4471
## Proportion 1
## ---------------------------------------------------------------------------
## suicideintent_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4453 18
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## suicideplan_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4459 12
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## suicideprep_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4456 15
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## suicideabort_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4454 17
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## suicidenumber_past
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4427 44
## Proportion 0.99 0.01
## ---------------------------------------------------------------------------
## suicidemethod_past
## n missing distinct value
## 4471 53 1 0
##
## Value 0
## Frequency 4471
## Proportion 1
## ---------------------------------------------------------------------------
## suicideattempt_past.1
## n missing distinct
## 4471 53 2
##
## Value 0 1
## Frequency 4443 28
## Proportion 0.994 0.006
## ---------------------------------------------------------------------------
# total item:
print(describe(currdata$kidsitotal))
## currdata$kidsitotal
## n missing distinct Info Mean Gmd .05 .10
## 4471 53 14 0.347 0.2691 0.4941 0 0
## .25 .50 .75 .90 .95
## 0 0 0 1 2
##
## Value 0 1 2 3 4 5 6 7 8 9
## Frequency 3877 352 114 39 29 24 18 5 4 2
## Proportion 0.867 0.079 0.025 0.009 0.006 0.005 0.004 0.001 0.001 0.000
##
## Value 10 11 12 14
## Frequency 4 1 1 1
## Proportion 0.001 0.000 0.000 0.000
hist(currdata$kidsitotal,main=paste("Histogram of Total Youth Suicid Items"))

# individual parent items:
factordata <- data.frame(lapply(currdata[,parentsuicidelabels], factor))
describe(factordata[,parentsuicidelabels])
## factordata[, parentsuicidelabels]
##
## 21 Variables 4524 Observations
## ---------------------------------------------------------------------------
## p_suicideAttempt_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4451 3
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## p_suicideAttempt_past
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4442 12
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## p_selfinjury_now
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
## p_selfinjury_past
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
## p_SImethod_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4445 9
## Proportion 0.998 0.002
## ---------------------------------------------------------------------------
## p_suicideintent_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4447 7
## Proportion 0.998 0.002
## ---------------------------------------------------------------------------
## p_suicidePlan_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4452 2
## Proportion 1 0
## ---------------------------------------------------------------------------
## p_suicidePrep_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4449 5
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## p_suicudeInterrupt_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4453 1
## Proportion 1 0
## ---------------------------------------------------------------------------
## p_suicidemethod_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4450 4
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## p_suicideTought_now
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4450 4
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## p_selfinjuryDeath_past
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
## p_selfinjuryThought_past
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
## p_SImethod_past
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
## p_suicideintent_past
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4441 13
## Proportion 0.997 0.003
## ---------------------------------------------------------------------------
## p_suicidePlan_past
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4451 3
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## p_suicidePrep_past
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4437 17
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## p_suicideInterrupt_past
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4447 7
## Proportion 0.998 0.002
## ---------------------------------------------------------------------------
## p_numSA_past
## n missing distinct
## 4454 70 2
##
## Value 0 1
## Frequency 4435 19
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## p_Samethod_past
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
## p_expectToDie_past
## n missing distinct value
## 4454 70 1 0
##
## Value 0
## Frequency 4454
## Proportion 1
## ---------------------------------------------------------------------------
# Rename some of the variables:
names(currdata)[names(currdata)=="highest.household.income"] <- "HHInc"
currdata$HHInc <- factor(currdata$HHInc,levels = c("[<50K]","[>=50K & <100K]","[>=100K]",""))
levels(currdata$HHInc) <- c("[<50K]","[50K - 100K]","[>100K]","_miss")
levels(currdata$high.educ) <- c("<= 12 grades","HS Degree","College Degree","Bachelor",
"Higher","_miss")
# Creating Quartiles of the first 10 Robust GFAs:
# Alternatively cut by z-scores of the factors < -.5, -.5 - .5, > .5
myqGFA <- paste0("qGFA",rep(1:8))
for(i in 1:length(myqGFA)){
currdata[,myqGFA[i]] <- as.factor(quantcut(currdata[,paste0("SMA_RGFA",i)]))
}
mynames <- names(currdata)
# General Sample Characteristics:
# Need to rename the demographic variables:
demovars <- c("age","female","race.ethnicity","high.educ","married",
"HHInc","anthro_1_height_in","anthroweight1lb","demo_prnt_age_v2")
# Additional Screen variables - youth reported hours a week:
addscreenvars <- mynames[grep("week_y_",mynames)]
listvars <- c(demovars,addscreenvars,"kidsitotal","parsitotal","KidsSIyes","ParSIyes")
tabledata <- currdata[,c(myqGFA,listvars)]
catVars = c("female","race.ethnicity","married","high.educ","HHInc","KidsSIyes","ParSIyes")
# length(myqGFA)
for(i in 1: length(myqGFA)){
mytable1 <- CreateTableOne(vars = listvars,data=tabledata,factorVars=catVars,strata=c(myqGFA[i]))
# Make the Table look nice:
tabAsStringMatrix <- print(mytable1, printToggle = FALSE, noSpaces = TRUE)
print(kable(tabAsStringMatrix, "html",caption = paste0("Quartiles of Robust GFA",i)) %>% kable_styling(bootstrap_options = c( "hover", "condensed", "responsive"),font_size = 11))
}
Quartiles of Robust GFA1
|
|
[-1.51,-0.636]
|
(-0.636,-0.245]
|
(-0.245,0.379]
|
(0.379,5.24]
|
p
|
test
|
|
n
|
1131
|
1131
|
1131
|
1131
|
|
|
|
age (mean (sd))
|
120.56 (7.18)
|
119.83 (7.46)
|
119.94 (7.29)
|
119.76 (7.40)
|
0.037
|
|
|
female = yes (%)
|
606 (53.6)
|
570 (50.4)
|
527 (46.6)
|
449 (39.7)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
<0.001
|
|
|
White
|
608 (53.8)
|
696 (61.5)
|
702 (62.1)
|
645 (57.1)
|
|
|
|
Black
|
151 (13.4)
|
84 (7.4)
|
96 (8.5)
|
109 (9.6)
|
|
|
|
Hispanic
|
254 (22.5)
|
209 (18.5)
|
199 (17.6)
|
227 (20.1)
|
|
|
|
Asian
|
28 (2.5)
|
32 (2.8)
|
28 (2.5)
|
15 (1.3)
|
|
|
|
Other
|
90 (8.0)
|
110 (9.7)
|
105 (9.3)
|
134 (11.9)
|
|
|
|
high.educ (%)
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
51 (4.5)
|
32 (2.8)
|
31 (2.7)
|
62 (5.5)
|
|
|
|
HS Degree
|
302 (26.7)
|
257 (22.7)
|
271 (24.0)
|
336 (29.7)
|
|
|
|
College Degree
|
153 (13.5)
|
118 (10.4)
|
129 (11.4)
|
157 (13.9)
|
|
|
|
Bachelor
|
335 (29.6)
|
364 (32.2)
|
370 (32.7)
|
319 (28.2)
|
|
|
|
Higher
|
289 (25.6)
|
360 (31.8)
|
329 (29.1)
|
254 (22.5)
|
|
|
|
_miss
|
1 (0.1)
|
0 (0.0)
|
1 (0.1)
|
3 (0.3)
|
|
|
|
married = yes (%)
|
817 (72.2)
|
848 (75.0)
|
804 (71.1)
|
736 (65.1)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
265 (23.4)
|
206 (18.2)
|
240 (21.2)
|
332 (29.4)
|
|
|
|
[50K - 100K]
|
287 (25.4)
|
330 (29.2)
|
319 (28.2)
|
327 (28.9)
|
|
|
|
[>100K]
|
472 (41.7)
|
521 (46.1)
|
490 (43.3)
|
378 (33.4)
|
|
|
|
_miss
|
107 (9.5)
|
74 (6.5)
|
82 (7.3)
|
94 (8.3)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.54 (3.09)
|
55.39 (3.18)
|
55.41 (3.17)
|
55.37 (3.20)
|
0.570
|
|
|
anthroweight1lb (mean (sd))
|
83.66 (23.02)
|
80.65 (21.97)
|
81.39 (22.35)
|
83.52 (23.86)
|
0.002
|
|
|
demo_prnt_age_v2 (mean (sd))
|
40.38 (6.81)
|
40.91 (6.66)
|
40.58 (6.54)
|
39.94 (7.09)
|
0.007
|
|
|
week_y_tvmovie (mean (sd))
|
8.52 (6.96)
|
8.71 (7.26)
|
8.40 (6.95)
|
9.79 (7.89)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
5.54 (6.94)
|
5.61 (6.96)
|
6.43 (7.96)
|
7.35 (8.45)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
6.02 (6.99)
|
6.49 (7.08)
|
7.12 (7.74)
|
8.20 (8.38)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
1.62 (3.77)
|
1.31 (3.05)
|
1.29 (3.21)
|
1.68 (3.97)
|
0.011
|
|
|
week_y_socnet (mean (sd))
|
0.68 (2.35)
|
0.58 (1.95)
|
0.61 (2.33)
|
0.96 (3.48)
|
0.001
|
|
|
week_y_chat (mean (sd))
|
1.18 (2.87)
|
1.03 (2.51)
|
1.11 (3.00)
|
1.30 (3.53)
|
0.153
|
|
|
kidsitotal (mean (sd))
|
0.14 (0.58)
|
0.17 (0.76)
|
0.27 (0.93)
|
0.50 (1.34)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.00 (0.04)
|
0.01 (0.11)
|
0.01 (0.16)
|
0.08 (0.51)
|
<0.001
|
|
|
KidsSIyes = 1 (%)
|
93 (8.3)
|
104 (9.4)
|
143 (12.8)
|
254 (22.7)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
2 (0.2)
|
3 (0.3)
|
5 (0.4)
|
39 (3.5)
|
<0.001
|
|
Quartiles of Robust GFA2
|
|
[-3.8,-0.637]
|
(-0.637,-0.0118]
|
(-0.0118,0.645]
|
(0.645,3.19]
|
p
|
test
|
|
n
|
1131
|
1131
|
1132
|
1130
|
|
|
|
age (mean (sd))
|
121.05 (7.29)
|
120.25 (7.34)
|
119.42 (7.31)
|
119.38 (7.29)
|
<0.001
|
|
|
female = yes (%)
|
575 (50.8)
|
568 (50.2)
|
531 (46.9)
|
478 (42.3)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
<0.001
|
|
|
White
|
801 (70.8)
|
738 (65.3)
|
659 (58.2)
|
453 (40.2)
|
|
|
|
Black
|
30 (2.7)
|
64 (5.7)
|
98 (8.7)
|
248 (22.0)
|
|
|
|
Hispanic
|
134 (11.8)
|
190 (16.8)
|
264 (23.3)
|
301 (26.7)
|
|
|
|
Asian
|
47 (4.2)
|
28 (2.5)
|
18 (1.6)
|
10 (0.9)
|
|
|
|
Other
|
119 (10.5)
|
111 (9.8)
|
93 (8.2)
|
116 (10.3)
|
|
|
|
high.educ (%)
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
5 (0.4)
|
19 (1.7)
|
43 (3.8)
|
109 (9.6)
|
|
|
|
HS Degree
|
152 (13.4)
|
235 (20.8)
|
315 (27.8)
|
464 (41.1)
|
|
|
|
College Degree
|
94 (8.3)
|
115 (10.2)
|
174 (15.4)
|
174 (15.4)
|
|
|
|
Bachelor
|
395 (34.9)
|
412 (36.4)
|
346 (30.6)
|
235 (20.8)
|
|
|
|
Higher
|
484 (42.8)
|
349 (30.9)
|
254 (22.4)
|
145 (12.8)
|
|
|
|
_miss
|
1 (0.1)
|
1 (0.1)
|
0 (0.0)
|
3 (0.3)
|
|
|
|
married = yes (%)
|
932 (82.4)
|
881 (77.9)
|
769 (67.9)
|
623 (55.1)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
123 (10.9)
|
194 (17.2)
|
259 (22.9)
|
467 (41.3)
|
|
|
|
[50K - 100K]
|
300 (26.5)
|
324 (28.6)
|
345 (30.5)
|
294 (26.0)
|
|
|
|
[>100K]
|
646 (57.1)
|
539 (47.7)
|
430 (38.0)
|
246 (21.8)
|
|
|
|
_miss
|
62 (5.5)
|
74 (6.5)
|
98 (8.7)
|
123 (10.9)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.70 (3.02)
|
55.50 (3.10)
|
55.27 (3.04)
|
55.25 (3.45)
|
0.001
|
|
|
anthroweight1lb (mean (sd))
|
79.50 (19.58)
|
81.07 (21.17)
|
82.40 (23.05)
|
86.25 (26.47)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
41.90 (5.97)
|
41.08 (6.05)
|
40.12 (7.11)
|
38.70 (7.47)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
6.76 (5.82)
|
8.25 (6.57)
|
9.48 (7.54)
|
10.94 (8.34)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
4.44 (6.24)
|
5.32 (6.70)
|
6.89 (8.07)
|
8.27 (8.71)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
5.49 (6.45)
|
6.13 (6.81)
|
7.49 (7.76)
|
8.73 (8.81)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
0.97 (2.37)
|
1.13 (2.61)
|
1.56 (3.57)
|
2.23 (4.86)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.39 (1.54)
|
0.51 (2.07)
|
0.75 (2.49)
|
1.17 (3.70)
|
<0.001
|
|
|
week_y_chat (mean (sd))
|
0.66 (1.53)
|
0.94 (2.20)
|
1.12 (2.64)
|
1.89 (4.59)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.25 (0.93)
|
0.21 (0.80)
|
0.26 (0.90)
|
0.35 (1.15)
|
0.005
|
|
|
parsitotal (mean (sd))
|
0.01 (0.16)
|
0.01 (0.19)
|
0.02 (0.22)
|
0.05 (0.44)
|
0.014
|
|
|
KidsSIyes = 1 (%)
|
152 (13.6)
|
117 (10.5)
|
150 (13.4)
|
175 (15.7)
|
0.004
|
|
|
ParSIyes = 1 (%)
|
10 (0.9)
|
8 (0.7)
|
12 (1.1)
|
19 (1.7)
|
0.130
|
|
Quartiles of Robust GFA3
|
|
[-2,-0.564]
|
(-0.564,-0.193]
|
(-0.193,0.287]
|
(0.287,8.66]
|
p
|
test
|
|
n
|
1135
|
1128
|
1130
|
1131
|
|
|
|
age (mean (sd))
|
119.02 (7.29)
|
120.01 (7.27)
|
120.42 (7.34)
|
120.65 (7.35)
|
<0.001
|
|
|
female = yes (%)
|
619 (54.5)
|
551 (48.8)
|
507 (44.9)
|
475 (42.0)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
<0.001
|
|
|
White
|
695 (61.3)
|
713 (63.2)
|
682 (60.4)
|
561 (49.6)
|
|
|
|
Black
|
85 (7.5)
|
71 (6.3)
|
95 (8.4)
|
189 (16.7)
|
|
|
|
Hispanic
|
241 (21.3)
|
212 (18.8)
|
188 (16.6)
|
248 (21.9)
|
|
|
|
Asian
|
24 (2.1)
|
32 (2.8)
|
27 (2.4)
|
20 (1.8)
|
|
|
|
Other
|
89 (7.8)
|
100 (8.9)
|
138 (12.2)
|
112 (9.9)
|
|
|
|
high.educ (%)
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
67 (5.9)
|
34 (3.0)
|
33 (2.9)
|
42 (3.7)
|
|
|
|
HS Degree
|
256 (22.6)
|
243 (21.5)
|
276 (24.4)
|
391 (34.6)
|
|
|
|
College Degree
|
134 (11.8)
|
117 (10.4)
|
133 (11.8)
|
173 (15.3)
|
|
|
|
Bachelor
|
364 (32.1)
|
373 (33.1)
|
349 (30.9)
|
302 (26.7)
|
|
|
|
Higher
|
312 (27.5)
|
361 (32.0)
|
338 (29.9)
|
221 (19.5)
|
|
|
|
_miss
|
2 (0.2)
|
0 (0.0)
|
1 (0.1)
|
2 (0.2)
|
|
|
|
married = yes (%)
|
827 (72.9)
|
855 (75.8)
|
826 (73.1)
|
697 (61.6)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
250 (22.0)
|
217 (19.2)
|
224 (19.8)
|
352 (31.1)
|
|
|
|
[50K - 100K]
|
306 (27.0)
|
311 (27.6)
|
317 (28.1)
|
329 (29.1)
|
|
|
|
[>100K]
|
474 (41.8)
|
526 (46.6)
|
505 (44.7)
|
356 (31.5)
|
|
|
|
_miss
|
105 (9.3)
|
74 (6.6)
|
84 (7.4)
|
94 (8.3)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.11 (3.12)
|
55.42 (3.04)
|
55.44 (3.06)
|
55.76 (3.38)
|
<0.001
|
|
|
anthroweight1lb (mean (sd))
|
80.31 (22.18)
|
80.31 (21.84)
|
81.45 (21.18)
|
87.15 (25.28)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
40.50 (6.88)
|
40.75 (6.31)
|
40.81 (6.72)
|
39.76 (7.16)
|
0.001
|
|
|
week_y_tvmovie (mean (sd))
|
5.54 (4.93)
|
7.15 (5.73)
|
9.26 (6.99)
|
13.49 (8.46)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
2.11 (2.76)
|
3.27 (4.15)
|
6.06 (6.35)
|
13.49 (9.48)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
2.65 (2.97)
|
4.04 (4.21)
|
7.02 (6.33)
|
14.13 (9.31)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
0.34 (0.84)
|
0.58 (1.01)
|
1.05 (1.46)
|
3.93 (6.13)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.08 (0.40)
|
0.21 (0.65)
|
0.39 (1.00)
|
2.14 (4.75)
|
<0.001
|
|
|
week_y_chat (mean (sd))
|
0.25 (0.67)
|
0.52 (1.01)
|
0.86 (1.44)
|
2.98 (5.27)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.24 (0.91)
|
0.22 (0.76)
|
0.25 (0.89)
|
0.37 (1.19)
|
0.001
|
|
|
parsitotal (mean (sd))
|
0.03 (0.31)
|
0.02 (0.30)
|
0.01 (0.11)
|
0.03 (0.32)
|
0.091
|
|
|
KidsSIyes = 1 (%)
|
132 (11.8)
|
135 (12.1)
|
149 (13.4)
|
178 (15.9)
|
0.018
|
|
|
ParSIyes = 1 (%)
|
16 (1.4)
|
9 (0.8)
|
6 (0.5)
|
18 (1.6)
|
0.049
|
|
Quartiles of Robust GFA4
|
|
[-3.75,-0.47]
|
(-0.47,0.111]
|
(0.111,0.528]
|
(0.528,7.52]
|
p
|
test
|
|
n
|
1132
|
1130
|
1131
|
1131
|
|
|
|
age (mean (sd))
|
119.92 (7.36)
|
119.74 (7.35)
|
120.10 (7.24)
|
120.34 (7.40)
|
0.240
|
|
|
female = yes (%)
|
311 (27.5)
|
447 (39.6)
|
617 (54.6)
|
777 (68.7)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
<0.001
|
|
|
White
|
590 (52.2)
|
663 (58.7)
|
731 (64.6)
|
667 (59.0)
|
|
|
|
Black
|
172 (15.2)
|
91 (8.1)
|
74 (6.5)
|
103 (9.1)
|
|
|
|
Hispanic
|
242 (21.4)
|
223 (19.8)
|
202 (17.9)
|
222 (19.6)
|
|
|
|
Asian
|
13 (1.1)
|
36 (3.2)
|
27 (2.4)
|
27 (2.4)
|
|
|
|
Other
|
114 (10.1)
|
116 (10.3)
|
97 (8.6)
|
112 (9.9)
|
|
|
|
high.educ (%)
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
50 (4.4)
|
42 (3.7)
|
39 (3.4)
|
45 (4.0)
|
|
|
|
HS Degree
|
390 (34.5)
|
273 (24.2)
|
242 (21.4)
|
261 (23.1)
|
|
|
|
College Degree
|
182 (16.1)
|
150 (13.3)
|
116 (10.3)
|
109 (9.6)
|
|
|
|
Bachelor
|
289 (25.5)
|
370 (32.7)
|
366 (32.4)
|
363 (32.1)
|
|
|
|
Higher
|
220 (19.4)
|
293 (25.9)
|
368 (32.5)
|
351 (31.0)
|
|
|
|
_miss
|
1 (0.1)
|
2 (0.2)
|
0 (0.0)
|
2 (0.2)
|
|
|
|
married = yes (%)
|
719 (63.5)
|
816 (72.2)
|
873 (77.2)
|
797 (70.5)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
362 (32.0)
|
248 (21.9)
|
195 (17.2)
|
238 (21.0)
|
|
|
|
[50K - 100K]
|
332 (29.3)
|
333 (29.5)
|
307 (27.1)
|
291 (25.7)
|
|
|
|
[>100K]
|
345 (30.5)
|
457 (40.4)
|
547 (48.4)
|
512 (45.3)
|
|
|
|
_miss
|
93 (8.2)
|
92 (8.1)
|
82 (7.3)
|
90 (8.0)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.38 (3.28)
|
55.47 (3.18)
|
55.42 (3.04)
|
55.46 (3.13)
|
0.893
|
|
|
anthroweight1lb (mean (sd))
|
84.83 (24.05)
|
82.18 (22.88)
|
79.93 (21.37)
|
82.28 (22.75)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
39.73 (7.18)
|
40.35 (6.62)
|
41.02 (6.37)
|
40.72 (6.87)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
14.07 (8.43)
|
9.22 (6.51)
|
6.56 (5.18)
|
5.58 (5.40)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
12.46 (9.42)
|
5.51 (6.07)
|
3.26 (4.53)
|
3.69 (5.71)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
14.68 (8.71)
|
6.14 (5.34)
|
3.68 (3.97)
|
3.32 (5.22)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
0.94 (2.12)
|
0.94 (2.18)
|
1.02 (2.31)
|
2.98 (5.67)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.31 (1.05)
|
0.35 (1.15)
|
0.36 (1.26)
|
1.80 (4.61)
|
<0.001
|
|
|
week_y_chat (mean (sd))
|
0.64 (1.72)
|
0.67 (1.81)
|
0.81 (1.77)
|
2.49 (4.92)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.39 (1.21)
|
0.27 (0.95)
|
0.20 (0.81)
|
0.22 (0.78)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.01 (0.24)
|
0.03 (0.26)
|
0.03 (0.28)
|
0.03 (0.31)
|
0.611
|
|
|
KidsSIyes = 1 (%)
|
193 (17.3)
|
155 (13.9)
|
118 (10.6)
|
128 (11.4)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
8 (0.7)
|
15 (1.3)
|
13 (1.2)
|
13 (1.2)
|
0.534
|
|
Quartiles of Robust GFA5
|
|
[-4.54,-0.612]
|
(-0.612,0.0165]
|
(0.0165,0.623]
|
(0.623,3.61]
|
p
|
test
|
|
n
|
1131
|
1132
|
1130
|
1131
|
|
|
|
age (mean (sd))
|
120.47 (7.23)
|
119.98 (7.46)
|
119.90 (7.40)
|
119.73 (7.25)
|
0.096
|
|
|
female = yes (%)
|
514 (45.4)
|
573 (50.6)
|
522 (46.2)
|
543 (48.0)
|
0.066
|
|
|
race.ethnicity (%)
|
|
|
|
|
<0.001
|
|
|
White
|
613 (54.2)
|
630 (55.8)
|
671 (59.4)
|
737 (65.2)
|
|
|
|
Black
|
131 (11.6)
|
121 (10.7)
|
104 (9.2)
|
84 (7.4)
|
|
|
|
Hispanic
|
249 (22.0)
|
251 (22.2)
|
206 (18.2)
|
183 (16.2)
|
|
|
|
Asian
|
27 (2.4)
|
27 (2.4)
|
32 (2.8)
|
17 (1.5)
|
|
|
|
Other
|
111 (9.8)
|
101 (8.9)
|
117 (10.4)
|
110 (9.7)
|
|
|
|
high.educ (%)
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
43 (3.8)
|
67 (5.9)
|
36 (3.2)
|
30 (2.7)
|
|
|
|
HS Degree
|
330 (29.2)
|
299 (26.4)
|
302 (26.7)
|
235 (20.8)
|
|
|
|
College Degree
|
138 (12.2)
|
136 (12.0)
|
155 (13.7)
|
128 (11.3)
|
|
|
|
Bachelor
|
332 (29.4)
|
341 (30.1)
|
349 (30.9)
|
366 (32.4)
|
|
|
|
Higher
|
287 (25.4)
|
287 (25.4)
|
286 (25.3)
|
372 (32.9)
|
|
|
|
_miss
|
1 (0.1)
|
2 (0.2)
|
2 (0.2)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
772 (68.3)
|
776 (68.6)
|
808 (71.5)
|
849 (75.1)
|
0.001
|
|
|
HHInc (%)
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
295 (26.1)
|
288 (25.4)
|
244 (21.6)
|
216 (19.1)
|
|
|
|
[50K - 100K]
|
311 (27.5)
|
310 (27.4)
|
338 (29.9)
|
304 (26.9)
|
|
|
|
[>100K]
|
430 (38.0)
|
434 (38.3)
|
456 (40.4)
|
541 (47.8)
|
|
|
|
_miss
|
95 (8.4)
|
100 (8.8)
|
92 (8.1)
|
70 (6.2)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.54 (3.17)
|
55.52 (3.17)
|
55.31 (3.15)
|
55.35 (3.15)
|
0.187
|
|
|
anthroweight1lb (mean (sd))
|
83.37 (24.11)
|
83.63 (23.39)
|
81.74 (22.30)
|
80.47 (21.34)
|
0.003
|
|
|
demo_prnt_age_v2 (mean (sd))
|
39.87 (6.91)
|
40.12 (6.75)
|
40.76 (7.15)
|
41.06 (6.23)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
8.97 (7.23)
|
9.00 (7.42)
|
8.91 (7.28)
|
8.54 (7.25)
|
0.417
|
|
|
week_y_video (mean (sd))
|
6.48 (7.74)
|
6.40 (7.82)
|
6.45 (7.61)
|
5.60 (7.35)
|
0.017
|
|
|
week_y_games (mean (sd))
|
7.40 (7.81)
|
6.80 (7.46)
|
7.22 (7.77)
|
6.41 (7.37)
|
0.009
|
|
|
week_y_text (mean (sd))
|
1.65 (3.92)
|
1.61 (3.84)
|
1.35 (3.20)
|
1.29 (3.06)
|
0.029
|
|
|
week_y_socnet (mean (sd))
|
0.70 (2.46)
|
0.94 (3.30)
|
0.60 (2.16)
|
0.58 (2.28)
|
0.003
|
|
|
week_y_chat (mean (sd))
|
1.15 (3.02)
|
1.24 (3.19)
|
1.11 (2.78)
|
1.12 (3.00)
|
0.729
|
|
|
kidsitotal (mean (sd))
|
0.27 (0.94)
|
0.28 (1.00)
|
0.25 (0.93)
|
0.28 (0.95)
|
0.780
|
|
|
parsitotal (mean (sd))
|
0.03 (0.22)
|
0.03 (0.40)
|
0.02 (0.23)
|
0.02 (0.19)
|
0.414
|
|
|
KidsSIyes = 1 (%)
|
145 (13.0)
|
155 (13.8)
|
144 (12.8)
|
150 (13.5)
|
0.893
|
|
|
ParSIyes = 1 (%)
|
17 (1.5)
|
11 (1.0)
|
11 (1.0)
|
10 (0.9)
|
0.447
|
|
Quartiles of Robust GFA6
|
|
[-5.54,-0.462]
|
(-0.462,-0.051]
|
(-0.051,0.485]
|
(0.485,3.85]
|
p
|
test
|
|
n
|
1131
|
1132
|
1130
|
1131
|
|
|
|
age (mean (sd))
|
119.43 (7.51)
|
120.16 (7.27)
|
119.99 (7.21)
|
120.51 (7.32)
|
0.005
|
|
|
female = yes (%)
|
508 (44.9)
|
558 (49.3)
|
560 (49.6)
|
526 (46.5)
|
0.077
|
|
|
race.ethnicity (%)
|
|
|
|
|
0.002
|
|
|
White
|
658 (58.2)
|
666 (58.9)
|
652 (57.7)
|
675 (59.7)
|
|
|
|
Black
|
131 (11.6)
|
116 (10.3)
|
104 (9.2)
|
89 (7.9)
|
|
|
|
Hispanic
|
192 (17.0)
|
220 (19.5)
|
240 (21.2)
|
237 (21.0)
|
|
|
|
Asian
|
22 (1.9)
|
37 (3.3)
|
28 (2.5)
|
16 (1.4)
|
|
|
|
Other
|
127 (11.2)
|
92 (8.1)
|
106 (9.4)
|
114 (10.1)
|
|
|
|
high.educ (%)
|
|
|
|
|
0.109
|
|
|
<= 12 grades
|
48 (4.2)
|
40 (3.5)
|
36 (3.2)
|
52 (4.6)
|
|
|
|
HS Degree
|
305 (27.0)
|
286 (25.3)
|
303 (26.8)
|
272 (24.0)
|
|
|
|
College Degree
|
121 (10.7)
|
138 (12.2)
|
132 (11.7)
|
166 (14.7)
|
|
|
|
Bachelor
|
348 (30.8)
|
347 (30.7)
|
335 (29.6)
|
358 (31.7)
|
|
|
|
Higher
|
308 (27.2)
|
318 (28.1)
|
324 (28.7)
|
282 (24.9)
|
|
|
|
_miss
|
1 (0.1)
|
3 (0.3)
|
0 (0.0)
|
1 (0.1)
|
|
|
|
married = yes (%)
|
762 (67.4)
|
821 (72.5)
|
831 (73.5)
|
791 (69.9)
|
0.006
|
|
|
HHInc (%)
|
|
|
|
|
0.040
|
|
|
[<50K]
|
274 (24.2)
|
238 (21.0)
|
257 (22.7)
|
274 (24.2)
|
|
|
|
[50K - 100K]
|
292 (25.8)
|
306 (27.0)
|
330 (29.2)
|
335 (29.6)
|
|
|
|
[>100K]
|
458 (40.5)
|
499 (44.1)
|
468 (41.4)
|
436 (38.5)
|
|
|
|
_miss
|
107 (9.5)
|
89 (7.9)
|
75 (6.6)
|
86 (7.6)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.28 (3.19)
|
55.54 (3.00)
|
55.44 (3.22)
|
55.46 (3.22)
|
0.257
|
|
|
anthroweight1lb (mean (sd))
|
80.87 (21.13)
|
82.02 (21.97)
|
83.24 (24.42)
|
83.08 (23.65)
|
0.050
|
|
|
demo_prnt_age_v2 (mean (sd))
|
40.53 (6.96)
|
40.62 (7.02)
|
40.55 (6.66)
|
40.12 (6.48)
|
0.285
|
|
|
week_y_tvmovie (mean (sd))
|
9.19 (7.73)
|
8.33 (6.80)
|
8.97 (7.27)
|
8.94 (7.33)
|
0.034
|
|
|
week_y_video (mean (sd))
|
6.27 (7.74)
|
5.51 (7.04)
|
5.89 (7.30)
|
7.25 (8.31)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
7.47 (8.10)
|
6.39 (7.08)
|
6.69 (7.37)
|
7.28 (7.82)
|
0.002
|
|
|
week_y_text (mean (sd))
|
1.59 (3.90)
|
1.48 (3.55)
|
1.43 (3.39)
|
1.39 (3.23)
|
0.588
|
|
|
week_y_socnet (mean (sd))
|
0.87 (3.19)
|
0.62 (2.12)
|
0.64 (2.39)
|
0.69 (2.54)
|
0.095
|
|
|
week_y_chat (mean (sd))
|
1.28 (3.63)
|
1.05 (2.31)
|
1.13 (2.96)
|
1.15 (2.95)
|
0.342
|
|
|
kidsitotal (mean (sd))
|
0.34 (1.08)
|
0.19 (0.75)
|
0.23 (0.86)
|
0.32 (1.08)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.04 (0.38)
|
0.01 (0.12)
|
0.01 (0.17)
|
0.04 (0.34)
|
0.003
|
|
|
KidsSIyes = 1 (%)
|
182 (16.3)
|
113 (10.1)
|
134 (12.0)
|
165 (14.7)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
14 (1.3)
|
7 (0.6)
|
4 (0.4)
|
24 (2.2)
|
<0.001
|
|
Quartiles of Robust GFA7
|
|
[-4.73,-0.523]
|
(-0.523,-0.101]
|
(-0.101,0.532]
|
(0.532,3.45]
|
p
|
test
|
|
n
|
1132
|
1130
|
1132
|
1130
|
|
|
|
age (mean (sd))
|
119.91 (7.35)
|
120.19 (7.36)
|
120.09 (7.28)
|
119.90 (7.36)
|
0.742
|
|
|
female = yes (%)
|
450 (39.8)
|
553 (48.9)
|
549 (48.5)
|
600 (53.1)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
0.874
|
|
|
White
|
669 (59.2)
|
666 (58.9)
|
670 (59.2)
|
646 (57.2)
|
|
|
|
Black
|
99 (8.8)
|
109 (9.6)
|
110 (9.7)
|
122 (10.8)
|
|
|
|
Hispanic
|
229 (20.2)
|
221 (19.6)
|
213 (18.8)
|
226 (20.0)
|
|
|
|
Asian
|
30 (2.7)
|
28 (2.5)
|
25 (2.2)
|
20 (1.8)
|
|
|
|
Other
|
104 (9.2)
|
106 (9.4)
|
113 (10.0)
|
116 (10.3)
|
|
|
|
high.educ (%)
|
|
|
|
|
0.013
|
|
|
<= 12 grades
|
55 (4.9)
|
43 (3.8)
|
32 (2.8)
|
46 (4.1)
|
|
|
|
HS Degree
|
287 (25.4)
|
256 (22.7)
|
295 (26.1)
|
328 (29.0)
|
|
|
|
College Degree
|
121 (10.7)
|
146 (12.9)
|
142 (12.5)
|
148 (13.1)
|
|
|
|
Bachelor
|
348 (30.7)
|
373 (33.0)
|
332 (29.3)
|
335 (29.6)
|
|
|
|
Higher
|
319 (28.2)
|
312 (27.6)
|
329 (29.1)
|
272 (24.1)
|
|
|
|
_miss
|
2 (0.2)
|
0 (0.0)
|
2 (0.2)
|
1 (0.1)
|
|
|
|
married = yes (%)
|
833 (73.6)
|
837 (74.1)
|
789 (69.7)
|
746 (66.0)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
0.007
|
|
|
[<50K]
|
260 (23.0)
|
230 (20.4)
|
269 (23.8)
|
284 (25.1)
|
|
|
|
[50K - 100K]
|
282 (24.9)
|
326 (28.8)
|
327 (28.9)
|
328 (29.0)
|
|
|
|
[>100K]
|
479 (42.3)
|
486 (43.0)
|
463 (40.9)
|
433 (38.3)
|
|
|
|
_miss
|
111 (9.8)
|
88 (7.8)
|
73 (6.4)
|
85 (7.5)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.28 (3.27)
|
55.50 (3.10)
|
55.47 (3.11)
|
55.47 (3.16)
|
0.314
|
|
|
anthroweight1lb (mean (sd))
|
80.91 (22.70)
|
82.82 (23.80)
|
82.40 (23.09)
|
83.08 (21.70)
|
0.108
|
|
|
demo_prnt_age_v2 (mean (sd))
|
40.39 (6.88)
|
40.70 (6.84)
|
40.47 (6.45)
|
40.27 (6.97)
|
0.493
|
|
|
week_y_tvmovie (mean (sd))
|
8.28 (7.16)
|
8.57 (6.97)
|
9.02 (7.48)
|
9.56 (7.51)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
5.65 (7.38)
|
5.80 (7.12)
|
6.22 (7.57)
|
7.25 (8.33)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
7.16 (7.73)
|
6.74 (7.38)
|
6.98 (7.67)
|
6.94 (7.66)
|
0.627
|
|
|
week_y_text (mean (sd))
|
1.77 (4.49)
|
1.34 (3.03)
|
1.41 (3.32)
|
1.38 (3.06)
|
0.013
|
|
|
week_y_socnet (mean (sd))
|
0.80 (3.28)
|
0.62 (2.10)
|
0.68 (2.37)
|
0.72 (2.46)
|
0.378
|
|
|
week_y_chat (mean (sd))
|
1.41 (3.87)
|
1.01 (2.27)
|
1.07 (2.72)
|
1.11 (2.89)
|
0.007
|
|
|
kidsitotal (mean (sd))
|
0.35 (1.08)
|
0.19 (0.77)
|
0.21 (0.80)
|
0.33 (1.11)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.04 (0.38)
|
0.01 (0.14)
|
0.01 (0.19)
|
0.03 (0.32)
|
0.020
|
|
|
KidsSIyes = 1 (%)
|
175 (15.6)
|
116 (10.4)
|
125 (11.2)
|
178 (15.9)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
20 (1.8)
|
6 (0.5)
|
7 (0.6)
|
16 (1.4)
|
0.010
|
|
Quartiles of Robust GFA8
|
|
[-2.86,-0.458]
|
(-0.458,0.0765]
|
(0.0765,0.491]
|
(0.491,3.35]
|
p
|
test
|
|
n
|
1131
|
1133
|
1129
|
1131
|
|
|
|
age (mean (sd))
|
119.89 (7.37)
|
120.01 (7.43)
|
120.13 (7.41)
|
120.06 (7.14)
|
0.892
|
|
|
female = yes (%)
|
587 (51.9)
|
614 (54.2)
|
554 (49.1)
|
397 (35.1)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
<0.001
|
|
|
White
|
659 (58.3)
|
700 (61.8)
|
707 (62.6)
|
585 (51.8)
|
|
|
|
Black
|
145 (12.8)
|
97 (8.6)
|
79 (7.0)
|
119 (10.5)
|
|
|
|
Hispanic
|
202 (17.9)
|
217 (19.2)
|
183 (16.2)
|
287 (25.4)
|
|
|
|
Asian
|
16 (1.4)
|
22 (1.9)
|
42 (3.7)
|
23 (2.0)
|
|
|
|
Other
|
109 (9.6)
|
97 (8.6)
|
118 (10.5)
|
115 (10.2)
|
|
|
|
high.educ (%)
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
46 (4.1)
|
38 (3.4)
|
36 (3.2)
|
56 (5.0)
|
|
|
|
HS Degree
|
323 (28.6)
|
235 (20.7)
|
247 (21.9)
|
361 (31.9)
|
|
|
|
College Degree
|
149 (13.2)
|
139 (12.3)
|
118 (10.5)
|
151 (13.4)
|
|
|
|
Bachelor
|
345 (30.5)
|
366 (32.3)
|
367 (32.5)
|
310 (27.4)
|
|
|
|
Higher
|
266 (23.5)
|
354 (31.2)
|
360 (31.9)
|
252 (22.3)
|
|
|
|
_miss
|
2 (0.2)
|
1 (0.1)
|
1 (0.1)
|
1 (0.1)
|
|
|
|
married = yes (%)
|
752 (66.5)
|
843 (74.4)
|
852 (75.5)
|
758 (67.0)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
296 (26.2)
|
227 (20.0)
|
221 (19.6)
|
299 (26.4)
|
|
|
|
[50K - 100K]
|
346 (30.6)
|
295 (26.0)
|
294 (26.0)
|
328 (29.0)
|
|
|
|
[>100K]
|
403 (35.6)
|
521 (46.0)
|
539 (47.7)
|
398 (35.2)
|
|
|
|
_miss
|
86 (7.6)
|
90 (7.9)
|
75 (6.6)
|
106 (9.4)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.51 (3.18)
|
55.44 (3.19)
|
55.49 (3.03)
|
55.29 (3.23)
|
0.343
|
|
|
anthroweight1lb (mean (sd))
|
84.87 (24.54)
|
80.54 (20.96)
|
80.34 (22.05)
|
83.46 (23.35)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
39.86 (7.07)
|
40.80 (6.34)
|
41.00 (6.79)
|
40.16 (6.87)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
17.25 (6.86)
|
8.49 (5.05)
|
5.41 (4.60)
|
4.27 (3.95)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
5.07 (6.93)
|
4.58 (6.42)
|
4.53 (5.86)
|
10.75 (9.08)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
7.41 (7.90)
|
5.64 (6.55)
|
5.26 (6.29)
|
9.51 (8.69)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
2.10 (4.90)
|
1.28 (3.03)
|
1.09 (2.62)
|
1.41 (3.02)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.95 (3.39)
|
0.65 (2.52)
|
0.52 (2.04)
|
0.71 (2.20)
|
0.001
|
|
|
week_y_chat (mean (sd))
|
1.12 (3.20)
|
1.01 (2.27)
|
0.95 (2.42)
|
1.54 (3.82)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.29 (1.00)
|
0.26 (0.96)
|
0.27 (1.02)
|
0.26 (0.83)
|
0.899
|
|
|
parsitotal (mean (sd))
|
0.03 (0.26)
|
0.04 (0.37)
|
0.01 (0.16)
|
0.02 (0.27)
|
0.176
|
|
|
KidsSIyes = 1 (%)
|
153 (13.7)
|
145 (12.9)
|
137 (12.3)
|
159 (14.2)
|
0.549
|
|
|
ParSIyes = 1 (%)
|
15 (1.3)
|
16 (1.4)
|
6 (0.5)
|
12 (1.1)
|
0.168
|
|
# by z-scores of the factors < -.5, -.5 - .5, > .5
mysdGFA <- paste0("sdGFA",rep(1:8))
for(i in 1:length(mysdGFA)){
currdata[,mysdGFA[i]] <- cut(currdata[,paste0("SMA_RGFA",i)], breaks = rep(-2.5:3.5))
}
mynames <- names(currdata)
# General Sample Characteristics:
# Need to rename the demographic variables:
demovars <- c("age","female","race.ethnicity","high.educ","married",
"HHInc","anthro_1_height_in","anthroweight1lb","demo_prnt_age_v2")
# Additional Screen variables - youth reported hours a week:
addscreenvars <- mynames[grep("week_y_",mynames)]
listvars <- c(demovars,addscreenvars,"kidsitotal","parsitotal","KidsSIyes","ParSIyes")
tabledata <- currdata[,c(mysdGFA,listvars)]
catVars = c("female","race.ethnicity","married","high.educ","HHInc","KidsSIyes","ParSIyes")
# length(myqGFA)
for(i in 1: length(mysdGFA)){
mytable1 <- CreateTableOne(vars = listvars,data=tabledata,factorVars=catVars,strata=c(mysdGFA[i]))
# Make the Table look nice:
tabAsStringMatrix <- print(mytable1, printToggle = FALSE, noSpaces = TRUE)
print(kable(tabAsStringMatrix, "html",caption = paste0("Standard Deviations of Robust GFA",i)) %>% kable_styling(bootstrap_options = c( "hover", "condensed", "responsive"),font_size = 11))
}
Standard Deviations of Robust GFA1
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
1
|
1529
|
1996
|
665
|
228
|
81
|
|
|
|
age (mean (sd))
|
108.00 (NA)
|
120.40 (7.20)
|
119.82 (7.38)
|
119.82 (7.51)
|
119.78 (7.12)
|
120.57 (7.77)
|
NA
|
|
|
female = yes (%)
|
1 (100.0)
|
797 (52.1)
|
968 (48.5)
|
266 (40.0)
|
90 (39.5)
|
23 (28.4)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
<0.001
|
|
|
White
|
0 (0.0)
|
855 (55.9)
|
1234 (61.9)
|
377 (56.8)
|
133 (58.3)
|
44 (54.3)
|
|
|
|
Black
|
1 (100.0)
|
180 (11.8)
|
157 (7.9)
|
58 (8.7)
|
28 (12.3)
|
11 (13.6)
|
|
|
|
Hispanic
|
0 (0.0)
|
330 (21.6)
|
356 (17.8)
|
143 (21.5)
|
40 (17.5)
|
13 (16.0)
|
|
|
|
Asian
|
0 (0.0)
|
37 (2.4)
|
53 (2.7)
|
11 (1.7)
|
2 (0.9)
|
0 (0.0)
|
|
|
|
Other
|
0 (0.0)
|
127 (8.3)
|
195 (9.8)
|
75 (11.3)
|
25 (11.0)
|
13 (16.0)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
0 (0.0)
|
62 (4.1)
|
56 (2.8)
|
39 (5.9)
|
10 (4.4)
|
7 (8.6)
|
|
|
|
HS Degree
|
0 (0.0)
|
387 (25.3)
|
479 (24.0)
|
197 (29.6)
|
62 (27.2)
|
29 (35.8)
|
|
|
|
College Degree
|
0 (0.0)
|
202 (13.2)
|
215 (10.8)
|
85 (12.8)
|
35 (15.4)
|
16 (19.8)
|
|
|
|
Bachelor
|
1 (100.0)
|
460 (30.1)
|
645 (32.3)
|
186 (28.0)
|
74 (32.5)
|
18 (22.2)
|
|
|
|
Higher
|
0 (0.0)
|
417 (27.3)
|
600 (30.1)
|
156 (23.5)
|
47 (20.6)
|
10 (12.3)
|
|
|
|
_miss
|
0 (0.0)
|
1 (0.1)
|
1 (0.1)
|
2 (0.3)
|
0 (0.0)
|
1 (1.2)
|
|
|
|
married = yes (%)
|
1 (100.0)
|
1126 (73.6)
|
1439 (72.1)
|
443 (66.6)
|
145 (63.6)
|
41 (50.6)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
0 (0.0)
|
329 (21.5)
|
405 (20.3)
|
197 (29.6)
|
72 (31.6)
|
29 (35.8)
|
|
|
|
[50K - 100K]
|
1 (100.0)
|
418 (27.3)
|
568 (28.5)
|
185 (27.8)
|
65 (28.5)
|
20 (24.7)
|
|
|
|
[>100K]
|
0 (0.0)
|
646 (42.2)
|
888 (44.5)
|
233 (35.0)
|
72 (31.6)
|
19 (23.5)
|
|
|
|
_miss
|
0 (0.0)
|
136 (8.9)
|
135 (6.8)
|
50 (7.5)
|
19 (8.3)
|
13 (16.0)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.50 (NA)
|
55.52 (3.11)
|
55.41 (3.17)
|
55.35 (3.23)
|
55.27 (3.18)
|
55.23 (3.19)
|
NA
|
|
|
anthroweight1lb (mean (sd))
|
106.50 (NA)
|
82.82 (23.02)
|
81.24 (21.94)
|
84.16 (24.47)
|
82.37 (24.29)
|
83.08 (23.72)
|
NA
|
|
|
demo_prnt_age_v2 (mean (sd))
|
34.00 (NA)
|
40.58 (6.81)
|
40.63 (6.56)
|
40.11 (6.85)
|
40.01 (7.24)
|
38.12 (7.89)
|
NA
|
|
|
week_y_tvmovie (mean (sd))
|
10.50 (NA)
|
8.64 (7.06)
|
8.44 (7.04)
|
9.63 (7.66)
|
10.59 (8.77)
|
10.80 (7.83)
|
NA
|
|
|
week_y_video (mean (sd))
|
4.50 (NA)
|
5.50 (6.85)
|
6.17 (7.66)
|
7.02 (7.99)
|
7.70 (9.24)
|
9.48 (9.85)
|
NA
|
|
|
week_y_games (mean (sd))
|
2.50 (NA)
|
6.24 (7.08)
|
6.78 (7.40)
|
7.80 (8.09)
|
8.90 (9.11)
|
10.92 (9.65)
|
NA
|
|
|
week_y_text (mean (sd))
|
24.00 (NA)
|
1.55 (3.56)
|
1.26 (3.13)
|
1.49 (3.49)
|
2.43 (5.39)
|
1.77 (4.07)
|
NA
|
|
|
week_y_socnet (mean (sd))
|
0.00 (NA)
|
0.65 (2.22)
|
0.60 (2.27)
|
0.86 (3.09)
|
1.46 (4.81)
|
0.39 (1.38)
|
NA
|
|
|
week_y_chat (mean (sd))
|
11.00 (NA)
|
1.16 (2.87)
|
1.05 (2.74)
|
1.22 (3.19)
|
1.72 (4.74)
|
0.88 (3.03)
|
NA
|
|
|
kidsitotal (mean (sd))
|
0.00 (NA)
|
0.14 (0.58)
|
0.23 (0.88)
|
0.43 (1.21)
|
0.61 (1.52)
|
0.96 (2.04)
|
NA
|
|
|
parsitotal (mean (sd))
|
0.00 (NA)
|
0.00 (0.06)
|
0.01 (0.14)
|
0.04 (0.26)
|
0.17 (0.80)
|
0.23 (0.92)
|
NA
|
|
|
KidsSIyes = 1 (%)
|
0 (0.0)
|
128 (8.5)
|
232 (11.7)
|
129 (19.5)
|
63 (28.0)
|
30 (38.0)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
0 (0.0)
|
3 (0.2)
|
7 (0.4)
|
16 (2.4)
|
14 (6.3)
|
6 (7.6)
|
<0.001
|
|
Standard Deviations of Robust GFA2
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
236
|
1085
|
1806
|
1077
|
263
|
21
|
|
|
|
age (mean (sd))
|
120.83 (6.95)
|
120.91 (7.26)
|
119.86 (7.39)
|
119.47 (7.28)
|
118.49 (7.40)
|
118.43 (7.08)
|
<0.001
|
|
|
female = yes (%)
|
123 (52.1)
|
546 (50.3)
|
875 (48.4)
|
476 (44.2)
|
106 (40.3)
|
6 (28.6)
|
0.002
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
<0.001
|
|
|
White
|
167 (70.8)
|
760 (70.0)
|
1121 (62.1)
|
506 (47.1)
|
72 (27.4)
|
2 (9.5)
|
|
|
|
Black
|
1 (0.4)
|
38 (3.5)
|
132 (7.3)
|
176 (16.4)
|
82 (31.2)
|
11 (52.4)
|
|
|
|
Hispanic
|
23 (9.7)
|
140 (12.9)
|
362 (20.0)
|
274 (25.5)
|
80 (30.4)
|
6 (28.6)
|
|
|
|
Asian
|
17 (7.2)
|
38 (3.5)
|
31 (1.7)
|
12 (1.1)
|
2 (0.8)
|
0 (0.0)
|
|
|
|
Other
|
28 (11.9)
|
109 (10.0)
|
160 (8.9)
|
107 (10.0)
|
27 (10.3)
|
2 (9.5)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
0 (0.0)
|
6 (0.6)
|
52 (2.9)
|
78 (7.2)
|
33 (12.5)
|
7 (33.3)
|
|
|
|
HS Degree
|
23 (9.7)
|
172 (15.9)
|
427 (23.6)
|
409 (38.0)
|
125 (47.5)
|
6 (28.6)
|
|
|
|
College Degree
|
12 (5.1)
|
101 (9.3)
|
232 (12.8)
|
172 (16.0)
|
34 (12.9)
|
5 (23.8)
|
|
|
|
Bachelor
|
69 (29.2)
|
388 (35.8)
|
620 (34.3)
|
259 (24.0)
|
38 (14.4)
|
0 (0.0)
|
|
|
|
Higher
|
132 (55.9)
|
417 (38.4)
|
474 (26.2)
|
157 (14.6)
|
33 (12.5)
|
2 (9.5)
|
|
|
|
_miss
|
0 (0.0)
|
1 (0.1)
|
1 (0.1)
|
2 (0.2)
|
0 (0.0)
|
1 (4.8)
|
|
|
|
married = yes (%)
|
208 (88.1)
|
861 (79.4)
|
1329 (73.6)
|
642 (59.6)
|
124 (47.1)
|
8 (38.1)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
15 (6.4)
|
136 (12.5)
|
371 (20.5)
|
370 (34.4)
|
136 (51.7)
|
12 (57.1)
|
|
|
|
[50K - 100K]
|
53 (22.5)
|
298 (27.5)
|
545 (30.2)
|
300 (27.9)
|
56 (21.3)
|
2 (9.5)
|
|
|
|
[>100K]
|
151 (64.0)
|
589 (54.3)
|
761 (42.1)
|
297 (27.6)
|
37 (14.1)
|
2 (9.5)
|
|
|
|
_miss
|
17 (7.2)
|
62 (5.7)
|
129 (7.1)
|
110 (10.2)
|
34 (12.9)
|
5 (23.8)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.85 (3.13)
|
55.66 (2.96)
|
55.39 (3.10)
|
55.32 (3.15)
|
54.81 (4.07)
|
55.48 (3.77)
|
0.001
|
|
|
anthroweight1lb (mean (sd))
|
79.70 (19.63)
|
79.96 (19.81)
|
81.70 (22.20)
|
84.94 (25.08)
|
87.33 (28.43)
|
90.98 (34.03)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
42.34 (5.04)
|
41.72 (6.16)
|
40.57 (6.62)
|
39.11 (7.18)
|
37.96 (8.22)
|
37.57 (7.06)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
5.58 (5.04)
|
7.30 (6.04)
|
8.82 (7.00)
|
10.59 (8.17)
|
11.51 (8.79)
|
13.71 (11.10)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
3.29 (4.83)
|
4.83 (6.52)
|
6.19 (7.49)
|
7.66 (8.47)
|
9.03 (8.99)
|
11.35 (10.03)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
4.35 (5.05)
|
5.86 (6.78)
|
6.90 (7.37)
|
7.99 (8.21)
|
9.71 (9.82)
|
13.57 (10.90)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
0.72 (1.21)
|
1.07 (2.64)
|
1.33 (3.05)
|
1.92 (4.43)
|
2.66 (5.35)
|
6.51 (8.49)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.23 (0.76)
|
0.43 (1.61)
|
0.64 (2.32)
|
0.98 (3.22)
|
1.26 (3.87)
|
5.57 (9.52)
|
<0.001
|
|
|
week_y_chat (mean (sd))
|
0.56 (1.68)
|
0.75 (1.83)
|
1.00 (2.35)
|
1.53 (3.74)
|
2.33 (5.17)
|
8.23 (11.07)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.30 (1.21)
|
0.25 (0.88)
|
0.23 (0.85)
|
0.32 (1.09)
|
0.38 (1.12)
|
0.14 (0.48)
|
0.066
|
|
|
parsitotal (mean (sd))
|
0.02 (0.20)
|
0.01 (0.13)
|
0.02 (0.21)
|
0.04 (0.35)
|
0.07 (0.60)
|
0.00 (0.00)
|
0.015
|
|
|
KidsSIyes = 1 (%)
|
30 (13.0)
|
142 (13.2)
|
214 (12.0)
|
156 (14.7)
|
44 (16.9)
|
2 (9.5)
|
0.167
|
|
|
ParSIyes = 1 (%)
|
3 (1.3)
|
7 (0.7)
|
17 (1.0)
|
16 (1.5)
|
6 (2.3)
|
0 (0.0)
|
0.177
|
|
Standard Deviations of Robust GFA3
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
14
|
1316
|
2350
|
591
|
137
|
50
|
|
|
|
age (mean (sd))
|
115.00 (5.33)
|
119.04 (7.29)
|
120.41 (7.36)
|
120.63 (7.21)
|
119.84 (7.10)
|
120.90 (7.20)
|
<0.001
|
|
|
female = yes (%)
|
5 (35.7)
|
715 (54.3)
|
1085 (46.2)
|
219 (37.1)
|
63 (46.0)
|
31 (62.0)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
<0.001
|
|
|
White
|
6 (42.9)
|
817 (62.1)
|
1434 (61.0)
|
315 (53.3)
|
47 (34.3)
|
17 (34.0)
|
|
|
|
Black
|
4 (28.6)
|
92 (7.0)
|
187 (8.0)
|
87 (14.7)
|
29 (21.2)
|
13 (26.0)
|
|
|
|
Hispanic
|
3 (21.4)
|
270 (20.5)
|
416 (17.7)
|
128 (21.7)
|
43 (31.4)
|
13 (26.0)
|
|
|
|
Asian
|
0 (0.0)
|
28 (2.1)
|
64 (2.7)
|
10 (1.7)
|
1 (0.7)
|
0 (0.0)
|
|
|
|
Other
|
1 (7.1)
|
108 (8.2)
|
248 (10.6)
|
51 (8.6)
|
17 (12.4)
|
7 (14.0)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
3 (21.4)
|
72 (5.5)
|
63 (2.7)
|
26 (4.4)
|
5 (3.6)
|
4 (8.0)
|
|
|
|
HS Degree
|
5 (35.7)
|
294 (22.3)
|
558 (23.7)
|
195 (33.0)
|
59 (43.1)
|
23 (46.0)
|
|
|
|
College Degree
|
2 (14.3)
|
145 (11.0)
|
283 (12.0)
|
94 (15.9)
|
19 (13.9)
|
5 (10.0)
|
|
|
|
Bachelor
|
2 (14.3)
|
419 (31.8)
|
737 (31.4)
|
160 (27.1)
|
42 (30.7)
|
13 (26.0)
|
|
|
|
Higher
|
2 (14.3)
|
384 (29.2)
|
708 (30.1)
|
115 (19.5)
|
12 (8.8)
|
5 (10.0)
|
|
|
|
_miss
|
0 (0.0)
|
2 (0.2)
|
1 (0.0)
|
1 (0.2)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
6 (42.9)
|
971 (73.8)
|
1729 (73.6)
|
367 (62.1)
|
82 (59.9)
|
19 (38.0)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
8 (57.1)
|
280 (21.3)
|
465 (19.8)
|
185 (31.3)
|
51 (37.2)
|
25 (50.0)
|
|
|
|
[50K - 100K]
|
4 (28.6)
|
352 (26.7)
|
664 (28.3)
|
172 (29.1)
|
45 (32.8)
|
10 (20.0)
|
|
|
|
[>100K]
|
1 (7.1)
|
570 (43.3)
|
1051 (44.7)
|
185 (31.3)
|
31 (22.6)
|
9 (18.0)
|
|
|
|
_miss
|
1 (7.1)
|
114 (8.7)
|
170 (7.2)
|
49 (8.3)
|
10 (7.3)
|
6 (12.0)
|
|
|
|
anthro_1_height_in (mean (sd))
|
54.84 (4.94)
|
55.16 (3.11)
|
55.46 (3.07)
|
55.64 (3.42)
|
55.84 (3.03)
|
56.59 (2.67)
|
<0.001
|
|
|
anthroweight1lb (mean (sd))
|
81.16 (27.18)
|
80.30 (22.21)
|
81.60 (21.54)
|
85.34 (25.02)
|
89.40 (24.84)
|
92.14 (27.97)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
38.36 (7.69)
|
40.65 (6.79)
|
40.75 (6.60)
|
39.65 (7.21)
|
38.43 (7.07)
|
40.26 (7.11)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
2.73 (1.92)
|
5.73 (5.00)
|
8.72 (6.72)
|
13.35 (8.43)
|
15.48 (9.24)
|
14.61 (8.80)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
1.66 (2.20)
|
2.17 (2.92)
|
5.39 (6.10)
|
13.67 (9.23)
|
18.23 (9.17)
|
15.76 (10.13)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
1.57 (1.98)
|
2.79 (3.11)
|
6.23 (6.14)
|
14.62 (9.23)
|
18.01 (9.05)
|
15.85 (9.65)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
0.09 (0.33)
|
0.34 (0.86)
|
0.95 (1.47)
|
2.20 (2.98)
|
6.45 (6.77)
|
11.07 (8.61)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.00 (0.00)
|
0.09 (0.41)
|
0.36 (0.96)
|
1.14 (2.11)
|
2.28 (3.46)
|
6.94 (7.80)
|
<0.001
|
|
|
week_y_chat (mean (sd))
|
0.04 (0.13)
|
0.27 (0.70)
|
0.76 (1.37)
|
1.80 (2.53)
|
4.59 (5.63)
|
7.65 (8.17)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.50 (0.85)
|
0.25 (0.91)
|
0.24 (0.86)
|
0.33 (1.08)
|
0.50 (1.71)
|
0.34 (1.04)
|
0.018
|
|
|
parsitotal (mean (sd))
|
0.14 (0.53)
|
0.03 (0.32)
|
0.01 (0.21)
|
0.04 (0.39)
|
0.02 (0.19)
|
0.00 (0.00)
|
0.109
|
|
|
KidsSIyes = 1 (%)
|
5 (35.7)
|
153 (11.8)
|
300 (12.9)
|
91 (15.6)
|
24 (17.8)
|
8 (16.0)
|
0.013
|
|
|
ParSIyes = 1 (%)
|
1 (7.1)
|
16 (1.2)
|
18 (0.8)
|
10 (1.7)
|
2 (1.5)
|
0 (0.0)
|
0.073
|
|
Standard Deviations of Robust GFA4
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
240
|
792
|
2239
|
1058
|
79
|
30
|
|
|
|
age (mean (sd))
|
119.40 (7.07)
|
119.98 (7.41)
|
119.96 (7.28)
|
120.21 (7.42)
|
121.00 (7.63)
|
120.63 (6.74)
|
0.519
|
|
|
female = yes (%)
|
49 (20.4)
|
238 (30.1)
|
1040 (46.4)
|
728 (68.8)
|
50 (63.3)
|
20 (66.7)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
<0.001
|
|
|
White
|
123 (51.2)
|
418 (52.8)
|
1380 (61.7)
|
659 (62.3)
|
34 (43.0)
|
5 (16.7)
|
|
|
|
Black
|
46 (19.2)
|
106 (13.4)
|
167 (7.5)
|
69 (6.5)
|
16 (20.3)
|
8 (26.7)
|
|
|
|
Hispanic
|
41 (17.1)
|
179 (22.6)
|
423 (18.9)
|
194 (18.3)
|
19 (24.1)
|
12 (40.0)
|
|
|
|
Asian
|
5 (2.1)
|
7 (0.9)
|
60 (2.7)
|
30 (2.8)
|
1 (1.3)
|
0 (0.0)
|
|
|
|
Other
|
25 (10.4)
|
81 (10.2)
|
208 (9.3)
|
106 (10.0)
|
9 (11.4)
|
5 (16.7)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
14 (5.8)
|
30 (3.8)
|
82 (3.7)
|
36 (3.4)
|
4 (5.1)
|
4 (13.3)
|
|
|
|
HS Degree
|
90 (37.5)
|
268 (33.8)
|
512 (22.9)
|
221 (20.9)
|
25 (31.6)
|
15 (50.0)
|
|
|
|
College Degree
|
50 (20.8)
|
117 (14.8)
|
264 (11.8)
|
104 (9.8)
|
7 (8.9)
|
2 (6.7)
|
|
|
|
Bachelor
|
50 (20.8)
|
209 (26.4)
|
736 (32.9)
|
341 (32.2)
|
26 (32.9)
|
7 (23.3)
|
|
|
|
Higher
|
36 (15.0)
|
167 (21.1)
|
643 (28.7)
|
355 (33.6)
|
17 (21.5)
|
2 (6.7)
|
|
|
|
_miss
|
0 (0.0)
|
1 (0.1)
|
2 (0.1)
|
1 (0.1)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
140 (58.3)
|
519 (65.5)
|
1668 (74.5)
|
771 (72.9)
|
45 (57.0)
|
15 (50.0)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
83 (34.6)
|
238 (30.1)
|
446 (19.9)
|
193 (18.2)
|
26 (32.9)
|
17 (56.7)
|
|
|
|
[50K - 100K]
|
73 (30.4)
|
231 (29.2)
|
637 (28.5)
|
277 (26.2)
|
15 (19.0)
|
7 (23.3)
|
|
|
|
[>100K]
|
59 (24.6)
|
262 (33.1)
|
985 (44.0)
|
503 (47.5)
|
31 (39.2)
|
5 (16.7)
|
|
|
|
_miss
|
25 (10.4)
|
61 (7.7)
|
171 (7.6)
|
85 (8.0)
|
7 (8.9)
|
1 (3.3)
|
|
|
|
anthro_1_height_in (mean (sd))
|
54.99 (3.56)
|
55.50 (3.17)
|
55.48 (3.10)
|
55.34 (3.14)
|
55.62 (2.93)
|
57.31 (3.60)
|
0.004
|
|
|
anthroweight1lb (mean (sd))
|
84.11 (23.81)
|
85.11 (23.78)
|
81.23 (22.27)
|
81.16 (21.93)
|
84.81 (23.10)
|
97.73 (31.00)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
38.75 (6.94)
|
40.12 (7.32)
|
40.66 (6.53)
|
40.99 (6.71)
|
39.14 (7.56)
|
38.20 (7.03)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
16.80 (8.28)
|
12.80 (8.05)
|
8.03 (6.08)
|
4.81 (4.30)
|
8.75 (6.85)
|
11.97 (9.09)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
16.37 (9.47)
|
10.61 (8.69)
|
4.50 (5.55)
|
2.71 (3.95)
|
10.10 (9.75)
|
9.66 (9.54)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
20.97 (7.64)
|
12.25 (7.57)
|
4.99 (4.91)
|
2.58 (3.68)
|
7.74 (8.56)
|
9.76 (8.74)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
0.73 (1.59)
|
1.03 (2.32)
|
0.97 (2.16)
|
1.67 (3.26)
|
7.96 (6.81)
|
14.16 (9.58)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
0.29 (0.92)
|
0.31 (1.10)
|
0.35 (1.21)
|
0.73 (1.65)
|
5.36 (6.64)
|
9.57 (8.04)
|
<0.001
|
|
|
week_y_chat (mean (sd))
|
0.71 (1.54)
|
0.65 (1.85)
|
0.73 (1.75)
|
1.42 (2.74)
|
6.94 (7.03)
|
11.72 (9.89)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.48 (1.31)
|
0.36 (1.14)
|
0.24 (0.88)
|
0.18 (0.67)
|
0.57 (1.47)
|
0.31 (0.85)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.01 (0.09)
|
0.02 (0.27)
|
0.03 (0.28)
|
0.03 (0.30)
|
0.00 (0.00)
|
0.03 (0.18)
|
0.790
|
|
|
KidsSIyes = 1 (%)
|
48 (20.3)
|
129 (16.5)
|
274 (12.4)
|
108 (10.3)
|
16 (20.3)
|
4 (13.8)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
2 (0.9)
|
5 (0.6)
|
28 (1.3)
|
11 (1.1)
|
0 (0.0)
|
1 (3.3)
|
0.474
|
|
Standard Deviations of Robust GFA5
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
263
|
977
|
1914
|
1020
|
268
|
31
|
|
|
|
age (mean (sd))
|
121.52 (6.92)
|
120.02 (7.29)
|
119.97 (7.52)
|
119.63 (7.25)
|
120.13 (7.02)
|
120.87 (6.08)
|
0.014
|
|
|
female = yes (%)
|
110 (41.8)
|
465 (47.6)
|
933 (48.7)
|
482 (47.3)
|
125 (46.6)
|
15 (48.4)
|
0.456
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
<0.001
|
|
|
White
|
147 (55.9)
|
531 (54.4)
|
1098 (57.4)
|
615 (60.3)
|
204 (76.1)
|
26 (83.9)
|
|
|
|
Black
|
36 (13.7)
|
102 (10.4)
|
196 (10.3)
|
84 (8.2)
|
15 (5.6)
|
1 (3.2)
|
|
|
|
Hispanic
|
49 (18.6)
|
223 (22.8)
|
387 (20.2)
|
195 (19.1)
|
24 (9.0)
|
1 (3.2)
|
|
|
|
Asian
|
10 (3.8)
|
22 (2.3)
|
47 (2.5)
|
22 (2.2)
|
2 (0.7)
|
0 (0.0)
|
|
|
|
Other
|
21 (8.0)
|
99 (10.1)
|
184 (9.6)
|
104 (10.2)
|
23 (8.6)
|
3 (9.7)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
12 (4.6)
|
42 (4.3)
|
87 (4.5)
|
35 (3.4)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
HS Degree
|
64 (24.3)
|
284 (29.1)
|
515 (26.9)
|
229 (22.5)
|
55 (20.5)
|
2 (6.5)
|
|
|
|
College Degree
|
30 (11.4)
|
127 (13.0)
|
235 (12.3)
|
138 (13.5)
|
17 (6.3)
|
3 (9.7)
|
|
|
|
Bachelor
|
82 (31.2)
|
289 (29.6)
|
577 (30.1)
|
322 (31.6)
|
91 (34.0)
|
12 (38.7)
|
|
|
|
Higher
|
74 (28.1)
|
235 (24.1)
|
496 (25.9)
|
296 (29.0)
|
105 (39.2)
|
14 (45.2)
|
|
|
|
_miss
|
1 (0.4)
|
0 (0.0)
|
4 (0.2)
|
0 (0.0)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
177 (67.3)
|
669 (68.5)
|
1332 (69.6)
|
751 (73.6)
|
217 (81.0)
|
26 (83.9)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
71 (27.0)
|
248 (25.4)
|
460 (24.0)
|
217 (21.3)
|
35 (13.1)
|
4 (12.9)
|
|
|
|
[50K - 100K]
|
61 (23.2)
|
280 (28.7)
|
544 (28.4)
|
284 (27.8)
|
68 (25.4)
|
5 (16.1)
|
|
|
|
[>100K]
|
112 (42.6)
|
360 (36.8)
|
755 (39.4)
|
445 (43.6)
|
153 (57.1)
|
21 (67.7)
|
|
|
|
_miss
|
19 (7.2)
|
89 (9.1)
|
155 (8.1)
|
74 (7.3)
|
12 (4.5)
|
1 (3.2)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.76 (3.15)
|
55.45 (3.21)
|
55.44 (3.15)
|
55.34 (3.11)
|
55.27 (3.39)
|
55.13 (2.57)
|
0.462
|
|
|
anthroweight1lb (mean (sd))
|
83.81 (24.56)
|
82.88 (23.82)
|
82.97 (22.88)
|
81.37 (22.29)
|
78.48 (19.76)
|
76.34 (19.13)
|
0.012
|
|
|
demo_prnt_age_v2 (mean (sd))
|
40.39 (6.77)
|
39.70 (6.94)
|
40.40 (6.92)
|
40.79 (6.50)
|
42.00 (6.13)
|
43.13 (5.51)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
8.82 (7.12)
|
9.15 (7.33)
|
8.88 (7.33)
|
8.75 (7.31)
|
8.38 (7.28)
|
8.03 (6.90)
|
0.654
|
|
|
week_y_video (mean (sd))
|
5.91 (7.22)
|
6.54 (7.89)
|
6.43 (7.71)
|
5.86 (7.49)
|
5.28 (7.08)
|
5.90 (6.69)
|
0.075
|
|
|
week_y_games (mean (sd))
|
6.47 (7.06)
|
7.60 (7.93)
|
6.95 (7.69)
|
6.68 (7.46)
|
6.07 (6.91)
|
7.13 (6.83)
|
0.022
|
|
|
week_y_text (mean (sd))
|
1.29 (3.22)
|
1.77 (4.10)
|
1.49 (3.58)
|
1.28 (3.07)
|
1.09 (2.07)
|
1.75 (5.17)
|
0.016
|
|
|
week_y_socnet (mean (sd))
|
0.49 (1.57)
|
0.81 (2.81)
|
0.78 (2.84)
|
0.60 (2.27)
|
0.44 (1.93)
|
0.38 (1.15)
|
0.074
|
|
|
week_y_chat (mean (sd))
|
0.76 (1.50)
|
1.31 (3.37)
|
1.16 (2.99)
|
1.05 (2.73)
|
1.27 (3.43)
|
1.25 (4.15)
|
0.114
|
|
|
kidsitotal (mean (sd))
|
0.35 (1.17)
|
0.26 (0.95)
|
0.26 (0.91)
|
0.28 (1.02)
|
0.26 (0.78)
|
0.35 (0.98)
|
0.716
|
|
|
parsitotal (mean (sd))
|
0.03 (0.25)
|
0.02 (0.21)
|
0.03 (0.35)
|
0.01 (0.17)
|
0.00 (0.06)
|
0.10 (0.54)
|
0.323
|
|
|
KidsSIyes = 1 (%)
|
38 (14.7)
|
121 (12.6)
|
250 (13.2)
|
132 (13.1)
|
38 (14.5)
|
6 (19.4)
|
0.813
|
|
|
ParSIyes = 1 (%)
|
5 (2.0)
|
13 (1.4)
|
18 (1.0)
|
10 (1.0)
|
1 (0.4)
|
1 (3.2)
|
0.370
|
|
Standard Deviations of Robust GFA6
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
155
|
820
|
2382
|
884
|
189
|
30
|
|
|
|
age (mean (sd))
|
119.19 (7.80)
|
119.60 (7.43)
|
120.07 (7.26)
|
120.56 (7.32)
|
120.01 (7.44)
|
119.47 (7.50)
|
0.082
|
|
|
female = yes (%)
|
66 (42.6)
|
382 (46.6)
|
1174 (49.3)
|
421 (47.6)
|
81 (42.9)
|
11 (36.7)
|
0.178
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
0.042
|
|
|
White
|
93 (60.0)
|
480 (58.6)
|
1386 (58.2)
|
534 (60.4)
|
106 (56.1)
|
23 (76.7)
|
|
|
|
Black
|
19 (12.3)
|
81 (9.9)
|
236 (9.9)
|
75 (8.5)
|
9 (4.8)
|
1 (3.3)
|
|
|
|
Hispanic
|
23 (14.8)
|
150 (18.3)
|
481 (20.2)
|
180 (20.4)
|
45 (23.8)
|
5 (16.7)
|
|
|
|
Asian
|
1 (0.6)
|
19 (2.3)
|
67 (2.8)
|
12 (1.4)
|
4 (2.1)
|
0 (0.0)
|
|
|
|
Other
|
19 (12.3)
|
89 (10.9)
|
211 (8.9)
|
83 (9.4)
|
25 (13.2)
|
1 (3.3)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
0.047
|
|
|
<= 12 grades
|
13 (8.4)
|
28 (3.4)
|
79 (3.3)
|
43 (4.9)
|
9 (4.8)
|
0 (0.0)
|
|
|
|
HS Degree
|
49 (31.6)
|
215 (26.2)
|
618 (25.9)
|
206 (23.3)
|
49 (25.9)
|
7 (23.3)
|
|
|
|
College Degree
|
18 (11.6)
|
83 (10.1)
|
283 (11.9)
|
132 (14.9)
|
25 (13.2)
|
6 (20.0)
|
|
|
|
Bachelor
|
42 (27.1)
|
263 (32.1)
|
720 (30.2)
|
276 (31.2)
|
63 (33.3)
|
11 (36.7)
|
|
|
|
Higher
|
33 (21.3)
|
230 (28.0)
|
679 (28.5)
|
226 (25.6)
|
43 (22.8)
|
6 (20.0)
|
|
|
|
_miss
|
0 (0.0)
|
1 (0.1)
|
3 (0.1)
|
1 (0.1)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
105 (67.7)
|
554 (67.6)
|
1739 (73.0)
|
628 (71.0)
|
128 (67.7)
|
15 (50.0)
|
0.004
|
|
|
HHInc (%)
|
|
|
|
|
|
|
0.003
|
|
|
[<50K]
|
49 (31.6)
|
185 (22.6)
|
521 (21.9)
|
195 (22.1)
|
58 (30.7)
|
10 (33.3)
|
|
|
|
[50K - 100K]
|
35 (22.6)
|
221 (27.0)
|
665 (27.9)
|
266 (30.1)
|
55 (29.1)
|
8 (26.7)
|
|
|
|
[>100K]
|
54 (34.8)
|
333 (40.6)
|
1026 (43.1)
|
358 (40.5)
|
58 (30.7)
|
10 (33.3)
|
|
|
|
_miss
|
17 (11.0)
|
81 (9.9)
|
170 (7.1)
|
65 (7.4)
|
18 (9.5)
|
2 (6.7)
|
|
|
|
anthro_1_height_in (mean (sd))
|
54.86 (3.27)
|
55.47 (3.14)
|
55.48 (3.12)
|
55.37 (3.21)
|
55.74 (3.21)
|
55.66 (3.41)
|
0.168
|
|
|
anthroweight1lb (mean (sd))
|
78.74 (19.32)
|
81.49 (21.68)
|
82.62 (23.11)
|
82.15 (22.90)
|
85.40 (23.50)
|
86.61 (28.15)
|
0.078
|
|
|
demo_prnt_age_v2 (mean (sd))
|
39.87 (7.24)
|
40.75 (6.94)
|
40.59 (6.82)
|
40.12 (6.47)
|
40.19 (6.66)
|
39.00 (6.11)
|
0.186
|
|
|
week_y_tvmovie (mean (sd))
|
10.73 (8.57)
|
8.77 (7.53)
|
8.65 (7.03)
|
8.81 (7.28)
|
9.22 (7.52)
|
10.38 (7.53)
|
0.016
|
|
|
week_y_video (mean (sd))
|
7.10 (8.82)
|
6.09 (7.63)
|
5.74 (7.17)
|
7.15 (8.32)
|
7.07 (7.92)
|
9.49 (9.35)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
9.51 (9.23)
|
6.98 (7.83)
|
6.59 (7.26)
|
7.18 (7.85)
|
6.98 (7.24)
|
10.10 (8.72)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
1.78 (4.54)
|
1.54 (3.77)
|
1.45 (3.45)
|
1.32 (3.33)
|
1.53 (2.75)
|
1.10 (1.88)
|
0.627
|
|
|
week_y_socnet (mean (sd))
|
0.94 (3.14)
|
0.78 (2.88)
|
0.65 (2.38)
|
0.63 (2.45)
|
0.73 (2.10)
|
1.01 (3.19)
|
0.540
|
|
|
week_y_chat (mean (sd))
|
1.36 (3.12)
|
1.26 (3.66)
|
1.08 (2.62)
|
1.11 (2.85)
|
1.30 (3.55)
|
1.00 (1.85)
|
0.572
|
|
|
kidsitotal (mean (sd))
|
0.59 (1.58)
|
0.27 (0.89)
|
0.21 (0.80)
|
0.26 (0.95)
|
0.51 (1.56)
|
0.57 (1.04)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.03 (0.20)
|
0.03 (0.35)
|
0.01 (0.14)
|
0.03 (0.28)
|
0.03 (0.23)
|
0.30 (1.21)
|
<0.001
|
|
|
KidsSIyes = 1 (%)
|
37 (23.9)
|
114 (14.1)
|
259 (11.0)
|
113 (12.9)
|
39 (20.7)
|
9 (30.0)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
3 (2.0)
|
7 (0.9)
|
11 (0.5)
|
16 (1.8)
|
4 (2.1)
|
2 (6.7)
|
<0.001
|
|
Standard Deviations of Robust GFA7
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
130
|
1023
|
2160
|
918
|
224
|
24
|
|
|
|
age (mean (sd))
|
119.82 (7.52)
|
120.07 (7.34)
|
120.10 (7.31)
|
119.93 (7.34)
|
120.10 (7.55)
|
118.62 (7.49)
|
0.926
|
|
|
female = yes (%)
|
31 (23.8)
|
450 (44.0)
|
1046 (48.4)
|
484 (52.7)
|
123 (54.9)
|
11 (45.8)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
0.204
|
|
|
White
|
85 (65.4)
|
596 (58.3)
|
1276 (59.1)
|
536 (58.4)
|
130 (58.0)
|
6 (25.0)
|
|
|
|
Black
|
12 (9.2)
|
93 (9.1)
|
206 (9.5)
|
90 (9.8)
|
30 (13.4)
|
5 (20.8)
|
|
|
|
Hispanic
|
20 (15.4)
|
211 (20.6)
|
417 (19.3)
|
184 (20.0)
|
39 (17.4)
|
8 (33.3)
|
|
|
|
Asian
|
3 (2.3)
|
28 (2.7)
|
51 (2.4)
|
15 (1.6)
|
6 (2.7)
|
0 (0.0)
|
|
|
|
Other
|
10 (7.7)
|
94 (9.2)
|
209 (9.7)
|
93 (10.1)
|
19 (8.5)
|
5 (20.8)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
0.030
|
|
|
<= 12 grades
|
5 (3.8)
|
51 (5.0)
|
71 (3.3)
|
37 (4.0)
|
8 (3.6)
|
3 (12.5)
|
|
|
|
HS Degree
|
31 (23.8)
|
266 (26.0)
|
521 (24.1)
|
270 (29.4)
|
58 (25.9)
|
8 (33.3)
|
|
|
|
College Degree
|
18 (13.8)
|
102 (10.0)
|
276 (12.8)
|
120 (13.1)
|
27 (12.1)
|
5 (20.8)
|
|
|
|
Bachelor
|
41 (31.5)
|
309 (30.2)
|
674 (31.2)
|
269 (29.3)
|
75 (33.5)
|
4 (16.7)
|
|
|
|
Higher
|
34 (26.2)
|
294 (28.7)
|
616 (28.5)
|
221 (24.1)
|
56 (25.0)
|
4 (16.7)
|
|
|
|
_miss
|
1 (0.8)
|
1 (0.1)
|
2 (0.1)
|
1 (0.1)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
98 (75.4)
|
753 (73.6)
|
1554 (71.9)
|
618 (67.3)
|
142 (63.4)
|
11 (45.8)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
0.007
|
|
|
[<50K]
|
33 (25.4)
|
227 (22.2)
|
474 (21.9)
|
224 (24.4)
|
56 (25.0)
|
12 (50.0)
|
|
|
|
[50K - 100K]
|
34 (26.2)
|
253 (24.7)
|
625 (28.9)
|
269 (29.3)
|
66 (29.5)
|
5 (20.8)
|
|
|
|
[>100K]
|
50 (38.5)
|
443 (43.3)
|
909 (42.1)
|
355 (38.7)
|
86 (38.4)
|
4 (16.7)
|
|
|
|
_miss
|
13 (10.0)
|
100 (9.8)
|
152 (7.0)
|
70 (7.6)
|
16 (7.1)
|
3 (12.5)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.26 (3.14)
|
55.29 (3.25)
|
55.49 (3.13)
|
55.42 (3.10)
|
55.76 (3.22)
|
54.60 (3.45)
|
0.199
|
|
|
anthroweight1lb (mean (sd))
|
84.14 (30.42)
|
80.58 (21.38)
|
82.71 (23.61)
|
82.62 (21.75)
|
84.37 (21.40)
|
84.55 (18.96)
|
0.090
|
|
|
demo_prnt_age_v2 (mean (sd))
|
40.02 (7.14)
|
40.51 (6.82)
|
40.57 (6.63)
|
40.04 (6.88)
|
41.36 (6.96)
|
38.74 (8.34)
|
0.075
|
|
|
week_y_tvmovie (mean (sd))
|
9.89 (8.60)
|
8.02 (6.81)
|
8.83 (7.27)
|
9.50 (7.55)
|
9.56 (7.34)
|
11.91 (7.93)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
6.16 (7.90)
|
5.46 (7.16)
|
6.08 (7.42)
|
7.10 (8.24)
|
7.55 (8.46)
|
7.39 (8.60)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
8.90 (8.40)
|
6.79 (7.44)
|
6.92 (7.58)
|
6.89 (7.63)
|
6.90 (7.67)
|
8.25 (9.27)
|
0.081
|
|
|
week_y_text (mean (sd))
|
1.39 (3.98)
|
1.78 (4.48)
|
1.39 (3.18)
|
1.27 (2.96)
|
1.71 (3.40)
|
2.62 (5.03)
|
0.009
|
|
|
week_y_socnet (mean (sd))
|
0.60 (2.67)
|
0.82 (3.33)
|
0.67 (2.28)
|
0.69 (2.36)
|
0.75 (2.72)
|
0.75 (1.89)
|
0.736
|
|
|
week_y_chat (mean (sd))
|
1.22 (3.40)
|
1.44 (3.90)
|
1.05 (2.55)
|
1.08 (2.91)
|
1.19 (2.72)
|
1.32 (2.02)
|
0.030
|
|
|
kidsitotal (mean (sd))
|
0.53 (1.39)
|
0.30 (1.00)
|
0.20 (0.79)
|
0.32 (1.06)
|
0.34 (1.24)
|
0.29 (0.62)
|
<0.001
|
|
|
parsitotal (mean (sd))
|
0.09 (0.44)
|
0.03 (0.30)
|
0.01 (0.17)
|
0.03 (0.33)
|
0.02 (0.24)
|
0.04 (0.20)
|
0.026
|
|
|
KidsSIyes = 1 (%)
|
29 (22.7)
|
142 (14.0)
|
229 (10.8)
|
142 (15.6)
|
34 (15.2)
|
5 (20.8)
|
<0.001
|
|
|
ParSIyes = 1 (%)
|
6 (4.7)
|
11 (1.1)
|
12 (0.6)
|
14 (1.5)
|
2 (0.9)
|
1 (4.2)
|
<0.001
|
|
Standard Deviations of Robust GFA8
|
|
(-2.5,-1.5]
|
(-1.5,-0.5]
|
(-0.5,0.5]
|
(0.5,1.5]
|
(1.5,2.5]
|
(2.5,3.5]
|
p
|
test
|
|
n
|
237
|
801
|
2355
|
958
|
136
|
23
|
|
|
|
age (mean (sd))
|
119.68 (7.27)
|
119.98 (7.41)
|
120.05 (7.40)
|
120.19 (7.18)
|
119.12 (7.05)
|
119.78 (5.74)
|
0.673
|
|
|
female = yes (%)
|
145 (61.2)
|
383 (47.8)
|
1221 (51.8)
|
346 (36.1)
|
42 (30.9)
|
4 (17.4)
|
<0.001
|
|
|
race.ethnicity (%)
|
|
|
|
|
|
|
<0.001
|
|
|
White
|
116 (48.9)
|
485 (60.5)
|
1465 (62.2)
|
495 (51.7)
|
72 (53.3)
|
10 (43.5)
|
|
|
|
Black
|
39 (16.5)
|
94 (11.7)
|
189 (8.0)
|
94 (9.8)
|
20 (14.8)
|
4 (17.4)
|
|
|
|
Hispanic
|
44 (18.6)
|
144 (18.0)
|
413 (17.5)
|
249 (26.0)
|
27 (20.0)
|
8 (34.8)
|
|
|
|
Asian
|
2 (0.8)
|
14 (1.7)
|
64 (2.7)
|
22 (2.3)
|
1 (0.7)
|
0 (0.0)
|
|
|
|
Other
|
36 (15.2)
|
64 (8.0)
|
224 (9.5)
|
97 (10.1)
|
15 (11.1)
|
1 (4.3)
|
|
|
|
high.educ (%)
|
|
|
|
|
|
|
<0.001
|
|
|
<= 12 grades
|
17 (7.2)
|
27 (3.4)
|
76 (3.2)
|
47 (4.9)
|
7 (5.1)
|
1 (4.3)
|
|
|
|
HS Degree
|
89 (37.6)
|
208 (26.0)
|
507 (21.5)
|
294 (30.7)
|
55 (40.4)
|
8 (34.8)
|
|
|
|
College Degree
|
35 (14.8)
|
110 (13.7)
|
263 (11.2)
|
124 (12.9)
|
15 (11.0)
|
9 (39.1)
|
|
|
|
Bachelor
|
46 (19.4)
|
264 (33.0)
|
766 (32.5)
|
265 (27.7)
|
38 (27.9)
|
5 (21.7)
|
|
|
|
Higher
|
50 (21.1)
|
190 (23.7)
|
741 (31.5)
|
227 (23.7)
|
21 (15.4)
|
0 (0.0)
|
|
|
|
_miss
|
0 (0.0)
|
2 (0.2)
|
2 (0.1)
|
1 (0.1)
|
0 (0.0)
|
0 (0.0)
|
|
|
|
married = yes (%)
|
143 (60.3)
|
547 (68.3)
|
1756 (74.6)
|
653 (68.2)
|
84 (61.8)
|
12 (52.2)
|
<0.001
|
|
|
HHInc (%)
|
|
|
|
|
|
|
<0.001
|
|
|
[<50K]
|
75 (31.6)
|
198 (24.7)
|
469 (19.9)
|
240 (25.1)
|
42 (30.9)
|
12 (52.2)
|
|
|
|
[50K - 100K]
|
75 (31.6)
|
249 (31.1)
|
613 (26.0)
|
277 (28.9)
|
42 (30.9)
|
6 (26.1)
|
|
|
|
[>100K]
|
67 (28.3)
|
291 (36.3)
|
1105 (46.9)
|
351 (36.6)
|
39 (28.7)
|
2 (8.7)
|
|
|
|
_miss
|
20 (8.4)
|
63 (7.9)
|
168 (7.1)
|
90 (9.4)
|
13 (9.6)
|
3 (13.0)
|
|
|
|
anthro_1_height_in (mean (sd))
|
55.74 (3.22)
|
55.42 (3.10)
|
55.46 (3.14)
|
55.33 (3.25)
|
54.92 (2.69)
|
56.13 (4.54)
|
0.145
|
|
|
anthroweight1lb (mean (sd))
|
88.46 (26.17)
|
83.75 (24.24)
|
80.57 (21.53)
|
83.52 (23.58)
|
81.69 (20.79)
|
92.12 (28.59)
|
<0.001
|
|
|
demo_prnt_age_v2 (mean (sd))
|
39.34 (7.11)
|
39.78 (6.94)
|
40.92 (6.57)
|
40.27 (6.77)
|
39.64 (7.78)
|
37.83 (6.51)
|
<0.001
|
|
|
week_y_tvmovie (mean (sd))
|
23.96 (3.87)
|
15.62 (6.11)
|
7.11 (5.20)
|
4.50 (4.02)
|
3.03 (3.08)
|
1.58 (1.87)
|
<0.001
|
|
|
week_y_video (mean (sd))
|
3.03 (4.35)
|
5.62 (7.31)
|
4.62 (6.24)
|
9.14 (8.17)
|
19.70 (7.81)
|
27.70 (1.11)
|
<0.001
|
|
|
week_y_games (mean (sd))
|
8.01 (8.12)
|
7.37 (7.89)
|
5.46 (6.44)
|
8.60 (8.14)
|
14.71 (9.44)
|
18.76 (10.84)
|
<0.001
|
|
|
week_y_text (mean (sd))
|
2.63 (5.67)
|
1.94 (4.56)
|
1.19 (2.84)
|
1.37 (2.94)
|
1.41 (2.65)
|
3.58 (6.50)
|
<0.001
|
|
|
week_y_socnet (mean (sd))
|
1.06 (3.50)
|
0.91 (3.32)
|
0.58 (2.27)
|
0.68 (2.24)
|
0.82 (1.84)
|
1.54 (2.84)
|
0.002
|
|
|
week_y_chat (mean (sd))
|
1.03 (2.78)
|
1.13 (3.25)
|
0.98 (2.39)
|
1.34 (3.35)
|
2.39 (5.24)
|
5.26 (8.24)
|
<0.001
|
|
|
kidsitotal (mean (sd))
|
0.33 (0.95)
|
0.29 (1.06)
|
0.26 (0.97)
|
0.26 (0.84)
|
0.32 (0.79)
|
0.17 (0.65)
|
0.821
|
|
|
parsitotal (mean (sd))
|
0.02 (0.20)
|
0.03 (0.28)
|
0.02 (0.28)
|
0.02 (0.29)
|
0.00 (0.00)
|
0.04 (0.21)
|
0.918
|
|
|
KidsSIyes = 1 (%)
|
41 (17.5)
|
102 (12.9)
|
292 (12.5)
|
130 (13.7)
|
27 (20.0)
|
2 (8.7)
|
0.059
|
|
|
ParSIyes = 1 (%)
|
3 (1.3)
|
11 (1.4)
|
23 (1.0)
|
11 (1.2)
|
0 (0.0)
|
1 (4.3)
|
0.453
|
|
# Set up the variables:
covars <- c("age","female","race.ethnicity","high.educ","married","HHInc","demo_prnt_age_v2")
colabels <- c("Age","Female","Race: Black","Race: Hispanic","Race: Asian","Race: Other","Parental Education: HS","Parental Education: College","Parental Education: Bachelor","Parental Education: > Bachelor","Married","Household Income: 50-100K","Household Income: > 100K","Household Income: miss","Parental Age")
## Select the nesting variables: site and twin status
nestvars <- c("site_name","FamilyID")
# Independent variables:
indepvars <- paste0("SMA_RGFA",rep(1:8))
# dependent variables:
depvars <- c("kidsitotal","parsitotal")
GFAselectLabel <- paste0("SMA_RGFA",rep(1:8))
# Creating a data frame:
glmmadmbdata <- currdata[complete.cases(currdata[,c(covars,nestvars,depvars,indepvars)]),c(covars,nestvars,depvars,indepvars)]
# Visualizing missing data
aggr(currdata[,c(covars,nestvars,depvars,indepvars)],col = c("blue","orange"),sortVars=TRUE,prop = FALSE, numbers = TRUE, combined = TRUE, cex.lab = 0.5, cex.axis =0.5, cex.numbers =0.5)

##
## Variables sorted by number of missings:
## Variable Count
## parsitotal 70
## kidsitotal 53
## demo_prnt_age_v2 43
## race.ethnicity 2
## age 0
## female 0
## high.educ 0
## married 0
## HHInc 0
## site_name 0
## FamilyID 0
## SMA_RGFA1 0
## SMA_RGFA2 0
## SMA_RGFA3 0
## SMA_RGFA4 0
## SMA_RGFA5 0
## SMA_RGFA6 0
## SMA_RGFA7 0
## SMA_RGFA8 0
mydepvar <- depvars[1]
# Poisson Model with standard zero inflation:
kidsi_cov_ZIP <- myglmmTMBall(mydepvar,"null",covars,nestvars,glmmadmbdata,"poisson",1)
summary(kidsi_cov_ZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ age + female + race.ethnicity + high.educ + married +
## HHInc + demo_prnt_age_v2 + (1 | site_name)
## Zero inflation: ~1
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5295.7 5417.1 -2628.9 5257.7 4376
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.03835 0.1958
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.287713 0.666468 -0.432 0.66596
## age 0.008809 0.005010 1.758 0.07870 .
## femaleyes -0.153409 0.075186 -2.040 0.04131 *
## race.ethnicityBlack -0.092226 0.140903 -0.655 0.51277
## race.ethnicityHispanic -0.601359 0.123956 -4.851 1.23e-06 ***
## race.ethnicityAsian 0.557539 0.176700 3.155 0.00160 **
## race.ethnicityOther -0.106349 0.114009 -0.933 0.35092
## high.educHS Degree 0.322970 0.268911 1.201 0.22974
## high.educCollege Degree 0.524344 0.279870 1.874 0.06100 .
## high.educBachelor 0.427334 0.275599 1.551 0.12101
## high.educHigher 0.267492 0.281748 0.949 0.34242
## high.educ_miss 0.535192 0.836874 0.640 0.52249
## marriedyes -0.228173 0.087056 -2.621 0.00877 **
## HHInc[50K - 100K] -0.243370 0.104648 -2.326 0.02004 *
## HHInc[>100K] -0.237761 0.113765 -2.090 0.03662 *
## HHInc_miss -0.433070 0.169179 -2.560 0.01047 *
## demo_prnt_age_v2 -0.005046 0.005924 -0.852 0.39437
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.54697 0.05274 29.33 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot_model(kidsi_cov_ZIP,title = "ZIP Covariates: Youth Suicide Items, standard zero inflation")

kidsi_sma_ZIP <- myglmmTMBall(mydepvar,indepvars,covars,nestvars,glmmadmbdata,"poisson",1)
summary(kidsi_sma_ZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 +
## SMA_RGFA5 + SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female +
## race.ethnicity + high.educ + married + HHInc + demo_prnt_age_v2 +
## (1 | site_name)
## Zero inflation: ~1
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5183.7 5356.2 -2564.8 5129.7 4368
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.0649 0.2548
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.631630 0.664875 -0.950 0.3421
## SMA_RGFA1 0.270817 0.030413 8.905 < 2e-16 ***
## SMA_RGFA2 0.179537 0.039740 4.518 6.25e-06 ***
## SMA_RGFA3 0.157472 0.029590 5.322 1.03e-07 ***
## SMA_RGFA4 -0.180015 0.031830 -5.656 1.55e-08 ***
## SMA_RGFA5 0.005761 0.034115 0.169 0.8659
## SMA_RGFA6 -0.008236 0.028576 -0.288 0.7732
## SMA_RGFA7 -0.004237 0.033900 -0.125 0.9005
## SMA_RGFA8 -0.049918 0.038989 -1.280 0.2004
## age 0.004140 0.004919 0.842 0.4000
## femaleyes -0.008176 0.077878 -0.105 0.9164
## race.ethnicityBlack -0.352280 0.140841 -2.501 0.0124 *
## race.ethnicityHispanic -0.507607 0.122478 -4.144 3.41e-05 ***
## race.ethnicityAsian 0.872363 0.183671 4.750 2.04e-06 ***
## race.ethnicityOther -0.232362 0.113001 -2.056 0.0398 *
## high.educHS Degree 0.463863 0.255575 1.815 0.0695 .
## high.educCollege Degree 0.548912 0.266188 2.062 0.0392 *
## high.educBachelor 0.583931 0.263019 2.220 0.0264 *
## high.educHigher 0.551252 0.270020 2.042 0.0412 *
## high.educ_miss 0.448188 0.855908 0.524 0.6005
## marriedyes -0.071178 0.088221 -0.807 0.4198
## HHInc[50K - 100K] -0.173915 0.103757 -1.676 0.0937 .
## HHInc[>100K] -0.074867 0.116141 -0.645 0.5192
## HHInc_miss -0.347560 0.165330 -2.102 0.0355 *
## demo_prnt_age_v2 -0.001006 0.005850 -0.172 0.8634
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.34416 0.06106 22.01 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot_model(kidsi_sma_ZIP,type="est",vline.color = "red",order.terms = c(1:48),show.values = TRUE,value.offset = .75,title = "ZIP Screen Media GFA: Total Youth Suicide Items, standard zero inflation")

# With parameterized zero inflation coefficients:
kidsi_cov_pZIP <- myglmmTMBall(mydepvar,"null",covars,nestvars,glmmadmbdata,"poisson",2)
summary(kidsi_cov_pZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ age + female + race.ethnicity + high.educ + married +
## HHInc + demo_prnt_age_v2 + (1 | site_name)
## Zero inflation:
## ~age + female + race.ethnicity + high.educ + married + HHInc +
## demo_prnt_age_v2 + (1 | site_name)
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5282.4 5512.4 -2605.2 5210.4 4359
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.0268 0.1637
## Number of obs: 4395, groups: site_name, 20
##
## Zero-inflation model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.05276 0.2297
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.241435 0.735876 -1.687 0.09160 .
## age 0.016245 0.005523 2.941 0.00327 **
## femaleyes -0.049145 0.079870 -0.615 0.53835
## race.ethnicityBlack -0.019083 0.142792 -0.134 0.89369
## race.ethnicityHispanic -0.591926 0.143425 -4.127 3.67e-05 ***
## race.ethnicityAsian 0.545136 0.181118 3.010 0.00261 **
## race.ethnicityOther -0.207016 0.129575 -1.598 0.11012
## high.educHS Degree 0.226943 0.314479 0.722 0.47051
## high.educCollege Degree 0.428824 0.323927 1.324 0.18556
## high.educBachelor 0.308806 0.320961 0.962 0.33599
## high.educHigher 0.120954 0.329141 0.367 0.71326
## high.educ_miss 0.190259 1.028413 0.185 0.85323
## marriedyes -0.182374 0.094151 -1.937 0.05274 .
## HHInc[50K - 100K] -0.271821 0.111490 -2.438 0.01477 *
## HHInc[>100K] -0.279924 0.121272 -2.308 0.02099 *
## HHInc_miss -0.426012 0.194408 -2.191 0.02843 *
## demo_prnt_age_v2 -0.001207 0.006349 -0.190 0.84923
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.773336 0.963299 -1.841 0.065636 .
## age 0.024016 0.007231 3.321 0.000896 ***
## femaleyes 0.418310 0.105092 3.980 6.88e-05 ***
## race.ethnicityBlack 0.294053 0.195439 1.505 0.132432
## race.ethnicityHispanic -0.026339 0.181171 -0.145 0.884409
## race.ethnicityAsian -0.043778 0.300127 -0.146 0.884027
## race.ethnicityOther -0.316557 0.175852 -1.800 0.071839 .
## high.educHS Degree -0.068647 0.361937 -0.190 0.849571
## high.educCollege Degree -0.066718 0.376836 -0.177 0.859470
## high.educBachelor -0.109332 0.373002 -0.293 0.769434
## high.educHigher -0.194319 0.381802 -0.509 0.610785
## high.educ_miss -1.149954 1.596462 -0.720 0.471332
## marriedyes 0.109657 0.128883 0.851 0.394869
## HHInc[50K - 100K] -0.176440 0.158223 -1.115 0.264793
## HHInc[>100K] -0.209483 0.174863 -1.198 0.230923
## HHInc_miss -0.139088 0.240464 -0.578 0.562985
## demo_prnt_age_v2 0.012351 0.008494 1.454 0.145916
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot_model(kidsi_cov_ZIP,title = "ZIP Covariates: Youth Suicide Items, parameterized standard zero inflation")

kidsi_sma_pZIP <- myglmmTMBall(mydepvar,indepvars,covars,nestvars,glmmadmbdata,"poisson",2)
summary(kidsi_sma_pZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 +
## SMA_RGFA5 + SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female +
## race.ethnicity + high.educ + married + HHInc + demo_prnt_age_v2 +
## (1 | site_name)
## Zero inflation:
## ~SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 + SMA_RGFA5 +
## SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female + race.ethnicity +
## high.educ + married + HHInc + demo_prnt_age_v2 + (1 | site_name)
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5086.9 5419.1 -2491.5 4982.9 4343
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.03801 0.195
## Number of obs: 4395, groups: site_name, 20
##
## Zero-inflation model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.08153 0.2855
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.796595 0.760427 -2.363 0.018147 *
## SMA_RGFA1 0.150937 0.033159 4.552 5.32e-06 ***
## SMA_RGFA2 0.161095 0.044219 3.643 0.000269 ***
## SMA_RGFA3 0.145464 0.032222 4.514 6.35e-06 ***
## SMA_RGFA4 -0.144378 0.035735 -4.040 5.34e-05 ***
## SMA_RGFA5 0.005826 0.037755 0.154 0.877360
## SMA_RGFA6 -0.032119 0.031518 -1.019 0.308168
## SMA_RGFA7 -0.038871 0.038668 -1.005 0.314777
## SMA_RGFA8 -0.042115 0.042059 -1.001 0.316660
## age 0.014251 0.005584 2.552 0.010713 *
## femaleyes 0.082558 0.086099 0.959 0.337620
## race.ethnicityBlack -0.272001 0.153604 -1.771 0.076595 .
## race.ethnicityHispanic -0.534914 0.147058 -3.637 0.000275 ***
## race.ethnicityAsian 0.705959 0.186036 3.795 0.000148 ***
## race.ethnicityOther -0.322950 0.132112 -2.445 0.014505 *
## high.educHS Degree 0.497293 0.335952 1.480 0.138807
## high.educCollege Degree 0.588085 0.343281 1.713 0.086688 .
## high.educBachelor 0.561256 0.342393 1.639 0.101169
## high.educHigher 0.486957 0.351634 1.385 0.166102
## high.educ_miss -0.036011 1.111725 -0.032 0.974160
## marriedyes -0.041464 0.099657 -0.416 0.677358
## HHInc[50K - 100K] -0.249227 0.113220 -2.201 0.027717 *
## HHInc[>100K] -0.189944 0.125993 -1.508 0.131663
## HHInc_miss -0.386429 0.199327 -1.939 0.052541 .
## demo_prnt_age_v2 0.003188 0.006452 0.494 0.621251
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.673567 1.057786 -1.582 0.11362
## SMA_RGFA1 -0.519031 0.054048 -9.603 < 2e-16 ***
## SMA_RGFA2 -0.047570 0.062658 -0.759 0.44773
## SMA_RGFA3 -0.104250 0.052059 -2.003 0.04523 *
## SMA_RGFA4 0.074173 0.053141 1.396 0.16278
## SMA_RGFA5 -0.002419 0.054169 -0.045 0.96438
## SMA_RGFA6 -0.006655 0.051490 -0.129 0.89716
## SMA_RGFA7 -0.037154 0.055772 -0.666 0.50531
## SMA_RGFA8 -0.036364 0.061159 -0.595 0.55213
## age 0.024438 0.007716 3.167 0.00154 **
## femaleyes 0.254070 0.118495 2.144 0.03202 *
## race.ethnicityBlack 0.196644 0.217887 0.903 0.36679
## race.ethnicityHispanic -0.093767 0.195009 -0.481 0.63063
## race.ethnicityAsian -0.146806 0.307360 -0.478 0.63291
## race.ethnicityOther -0.319937 0.191950 -1.667 0.09556 .
## high.educHS Degree 0.109608 0.427783 0.256 0.79778
## high.educCollege Degree 0.042918 0.442033 0.097 0.92265
## high.educBachelor -0.054545 0.439962 -0.124 0.90133
## high.educHigher -0.147065 0.449414 -0.327 0.74349
## high.educ_miss -1.023216 2.199266 -0.465 0.64175
## marriedyes 0.048824 0.139015 0.351 0.72543
## HHInc[50K - 100K] -0.310991 0.168712 -1.843 0.06528 .
## HHInc[>100K] -0.371627 0.186472 -1.993 0.04627 *
## HHInc_miss -0.208031 0.260568 -0.798 0.42465
## demo_prnt_age_v2 0.013092 0.008973 1.459 0.14453
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot_model(kidsi_sma_ZIP,type="est",vline.color = "red",order.terms = c(1:48),show.values = TRUE,value.offset = .75,title = "ZIP Screen Media GFA: Total Youth Suicide Items, standard zero inflation")

# Negative Binomial Model
# Unfortunately the coefficient plot does not work with nbinom
# could use a self-made plot from here:
# https://github.com/glmmTMB/glmmTMB/blob/master/misc/salamanders.rmd
# https://www.fromthebottomoftheheap.net/2017/05/04/compare-mgcv-with-glmmTMB/
# without zero inflation coefficients:
kidsi_cov_ZINB <- myglmmTMBall(mydepvar,"null",covars,nestvars,glmmadmbdata,"nbinom2",1)
summary(kidsi_cov_ZINB)
## Family: nbinom2 ( log )
## Formula:
## kidsitotal ~ age + female + race.ethnicity + high.educ + married +
## HHInc + demo_prnt_age_v2 + (1 | site_name)
## Zero inflation: ~1
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5037.4 5165.2 -2498.7 4997.4 4375
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.04053 0.2013
## Number of obs: 4395, groups: site_name, 20
##
## Overdispersion parameter for nbinom2 family (): 0.132
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.363242 0.956762 -0.380 0.704199
## age -0.002915 0.007261 -0.401 0.688075
## femaleyes -0.372921 0.106119 -3.514 0.000441 ***
## race.ethnicityBlack -0.250153 0.193782 -1.291 0.196740
## race.ethnicityHispanic -0.557152 0.160487 -3.472 0.000517 ***
## race.ethnicityAsian 0.623805 0.328237 1.900 0.057371 .
## race.ethnicityOther 0.060307 0.178928 0.337 0.736081
## high.educHS Degree 0.335598 0.325887 1.030 0.303106
## high.educCollege Degree 0.497772 0.344569 1.445 0.148564
## high.educBachelor 0.420569 0.335751 1.253 0.210344
## high.educHigher 0.345124 0.345630 0.999 0.318019
## high.educ_miss 0.968624 1.602284 0.605 0.545493
## marriedyes -0.297675 0.130243 -2.286 0.022282 *
## HHInc[50K - 100K] -0.136530 0.157948 -0.864 0.387371
## HHInc[>100K] -0.101480 0.171444 -0.592 0.553908
## HHInc_miss -0.364589 0.230175 -1.584 0.113202
## demo_prnt_age_v2 -0.011077 0.008706 -1.272 0.203283
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -16.39 2128.55 -0.008 0.994
kidsi_sma_ZINB <- myglmmTMBall(mydepvar,indepvars,covars,nestvars,glmmadmbdata,"nbinom2",1)
summary(kidsi_sma_ZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 +
## SMA_RGFA5 + SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female +
## race.ethnicity + high.educ + married + HHInc + demo_prnt_age_v2 +
## (1 | site_name)
## Zero inflation: ~1
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5183.7 5356.2 -2564.8 5129.7 4368
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.0649 0.2548
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.631630 0.664875 -0.950 0.3421
## SMA_RGFA1 0.270817 0.030413 8.905 < 2e-16 ***
## SMA_RGFA2 0.179537 0.039740 4.518 6.25e-06 ***
## SMA_RGFA3 0.157472 0.029590 5.322 1.03e-07 ***
## SMA_RGFA4 -0.180015 0.031830 -5.656 1.55e-08 ***
## SMA_RGFA5 0.005761 0.034115 0.169 0.8659
## SMA_RGFA6 -0.008236 0.028576 -0.288 0.7732
## SMA_RGFA7 -0.004237 0.033900 -0.125 0.9005
## SMA_RGFA8 -0.049918 0.038989 -1.280 0.2004
## age 0.004140 0.004919 0.842 0.4000
## femaleyes -0.008176 0.077878 -0.105 0.9164
## race.ethnicityBlack -0.352280 0.140841 -2.501 0.0124 *
## race.ethnicityHispanic -0.507607 0.122478 -4.144 3.41e-05 ***
## race.ethnicityAsian 0.872363 0.183671 4.750 2.04e-06 ***
## race.ethnicityOther -0.232362 0.113001 -2.056 0.0398 *
## high.educHS Degree 0.463863 0.255575 1.815 0.0695 .
## high.educCollege Degree 0.548912 0.266188 2.062 0.0392 *
## high.educBachelor 0.583931 0.263019 2.220 0.0264 *
## high.educHigher 0.551252 0.270020 2.042 0.0412 *
## high.educ_miss 0.448188 0.855908 0.524 0.6005
## marriedyes -0.071178 0.088221 -0.807 0.4198
## HHInc[50K - 100K] -0.173915 0.103757 -1.676 0.0937 .
## HHInc[>100K] -0.074867 0.116141 -0.645 0.5192
## HHInc_miss -0.347560 0.165330 -2.102 0.0355 *
## demo_prnt_age_v2 -0.001006 0.005850 -0.172 0.8634
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.34416 0.06106 22.01 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
kidsi_sma_pZINB <- myglmmTMBall(mydepvar,indepvars,covars,nestvars,glmmadmbdata,"poisson",2)
summary(kidsi_sma_pZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 +
## SMA_RGFA5 + SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female +
## race.ethnicity + high.educ + married + HHInc + demo_prnt_age_v2 +
## (1 | site_name)
## Zero inflation:
## ~SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 + SMA_RGFA5 +
## SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female + race.ethnicity +
## high.educ + married + HHInc + demo_prnt_age_v2 + (1 | site_name)
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 5086.9 5419.1 -2491.5 4982.9 4343
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.03801 0.195
## Number of obs: 4395, groups: site_name, 20
##
## Zero-inflation model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.08153 0.2855
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.796595 0.760427 -2.363 0.018147 *
## SMA_RGFA1 0.150937 0.033159 4.552 5.32e-06 ***
## SMA_RGFA2 0.161095 0.044219 3.643 0.000269 ***
## SMA_RGFA3 0.145464 0.032222 4.514 6.35e-06 ***
## SMA_RGFA4 -0.144378 0.035735 -4.040 5.34e-05 ***
## SMA_RGFA5 0.005826 0.037755 0.154 0.877360
## SMA_RGFA6 -0.032119 0.031518 -1.019 0.308168
## SMA_RGFA7 -0.038871 0.038668 -1.005 0.314777
## SMA_RGFA8 -0.042115 0.042059 -1.001 0.316660
## age 0.014251 0.005584 2.552 0.010713 *
## femaleyes 0.082558 0.086099 0.959 0.337620
## race.ethnicityBlack -0.272001 0.153604 -1.771 0.076595 .
## race.ethnicityHispanic -0.534914 0.147058 -3.637 0.000275 ***
## race.ethnicityAsian 0.705959 0.186036 3.795 0.000148 ***
## race.ethnicityOther -0.322950 0.132112 -2.445 0.014505 *
## high.educHS Degree 0.497293 0.335952 1.480 0.138807
## high.educCollege Degree 0.588085 0.343281 1.713 0.086688 .
## high.educBachelor 0.561256 0.342393 1.639 0.101169
## high.educHigher 0.486957 0.351634 1.385 0.166102
## high.educ_miss -0.036011 1.111725 -0.032 0.974160
## marriedyes -0.041464 0.099657 -0.416 0.677358
## HHInc[50K - 100K] -0.249227 0.113220 -2.201 0.027717 *
## HHInc[>100K] -0.189944 0.125993 -1.508 0.131663
## HHInc_miss -0.386429 0.199327 -1.939 0.052541 .
## demo_prnt_age_v2 0.003188 0.006452 0.494 0.621251
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Zero-inflation model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.673567 1.057786 -1.582 0.11362
## SMA_RGFA1 -0.519031 0.054048 -9.603 < 2e-16 ***
## SMA_RGFA2 -0.047570 0.062658 -0.759 0.44773
## SMA_RGFA3 -0.104250 0.052059 -2.003 0.04523 *
## SMA_RGFA4 0.074173 0.053141 1.396 0.16278
## SMA_RGFA5 -0.002419 0.054169 -0.045 0.96438
## SMA_RGFA6 -0.006655 0.051490 -0.129 0.89716
## SMA_RGFA7 -0.037154 0.055772 -0.666 0.50531
## SMA_RGFA8 -0.036364 0.061159 -0.595 0.55213
## age 0.024438 0.007716 3.167 0.00154 **
## femaleyes 0.254070 0.118495 2.144 0.03202 *
## race.ethnicityBlack 0.196644 0.217887 0.903 0.36679
## race.ethnicityHispanic -0.093767 0.195009 -0.481 0.63063
## race.ethnicityAsian -0.146806 0.307360 -0.478 0.63291
## race.ethnicityOther -0.319937 0.191950 -1.667 0.09556 .
## high.educHS Degree 0.109608 0.427783 0.256 0.79778
## high.educCollege Degree 0.042918 0.442033 0.097 0.92265
## high.educBachelor -0.054545 0.439962 -0.124 0.90133
## high.educHigher -0.147065 0.449414 -0.327 0.74349
## high.educ_miss -1.023216 2.199266 -0.465 0.64175
## marriedyes 0.048824 0.139015 0.351 0.72543
## HHInc[50K - 100K] -0.310991 0.168712 -1.843 0.06528 .
## HHInc[>100K] -0.371627 0.186472 -1.993 0.04627 *
## HHInc_miss -0.208031 0.260568 -0.798 0.42465
## demo_prnt_age_v2 0.013092 0.008973 1.459 0.14453
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Non zero-inflated models
kidsi_sma_nZINB <- myglmmTMBall(mydepvar,indepvars,covars,nestvars,glmmadmbdata,"nbinom2",0)
summary(kidsi_sma_nZINB)
## Family: nbinom2 ( log )
## Formula:
## kidsitotal ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 +
## SMA_RGFA5 + SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female +
## race.ethnicity + high.educ + married + HHInc + demo_prnt_age_v2 +
## (1 | site_name)
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 4900.0 5072.5 -2423.0 4846.0 4368
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.08234 0.2869
## Number of obs: 4395, groups: site_name, 20
##
## Overdispersion parameter for nbinom2 family (): 0.17
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.569366 0.944845 -0.603 0.546773
## SMA_RGFA1 0.567331 0.054598 10.391 < 2e-16 ***
## SMA_RGFA2 0.217421 0.056221 3.867 0.000110 ***
## SMA_RGFA3 0.178284 0.051807 3.441 0.000579 ***
## SMA_RGFA4 -0.213371 0.052503 -4.064 4.82e-05 ***
## SMA_RGFA5 0.002363 0.049728 0.048 0.962104
## SMA_RGFA6 -0.008862 0.048990 -0.181 0.856458
## SMA_RGFA7 -0.025933 0.054319 -0.477 0.633069
## SMA_RGFA8 -0.050206 0.059887 -0.838 0.401836
## age -0.009226 0.007126 -1.295 0.195398
## femaleyes -0.133102 0.110337 -1.206 0.227695
## race.ethnicityBlack -0.474283 0.202785 -2.339 0.019343 *
## race.ethnicityHispanic -0.333063 0.162275 -2.052 0.040125 *
## race.ethnicityAsian 0.888068 0.305061 2.911 0.003601 **
## race.ethnicityOther -0.032561 0.175051 -0.186 0.852440
## high.educHS Degree 0.609914 0.325780 1.872 0.061184 .
## high.educCollege Degree 0.667092 0.343698 1.941 0.052268 .
## high.educBachelor 0.736175 0.337593 2.181 0.029209 *
## high.educHigher 0.759336 0.347056 2.188 0.028674 *
## high.educ_miss 0.775996 1.509043 0.514 0.607091
## marriedyes -0.118224 0.127537 -0.927 0.353936
## HHInc[50K - 100K] -0.004128 0.157069 -0.026 0.979035
## HHInc[>100K] 0.142491 0.170313 0.837 0.402794
## HHInc_miss -0.173630 0.226275 -0.767 0.442879
## demo_prnt_age_v2 -0.009669 0.008501 -1.137 0.255345
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot_model(kidsi_sma_nZINB,type="est",vline.color = "red",order.terms = c(1:24),show.values = TRUE,value.offset = .75,title = "nZINB Screen Media GFA: Total Youth Suicide Items, no zero inflation")

kidsi_sma_nZIP <- myglmmTMBall(mydepvar,indepvars,covars,nestvars,glmmadmbdata,"poisson",0)
summary(kidsi_sma_nZIP)
## Family: poisson ( log )
## Formula:
## kidsitotal ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 +
## SMA_RGFA5 + SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female +
## race.ethnicity + high.educ + married + HHInc + demo_prnt_age_v2 +
## (1 | site_name)
## Data: dat
##
## AIC BIC logLik deviance df.resid
## 6265.9 6432.0 -3107.0 6213.9 4369
##
## Random effects:
##
## Conditional model:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.1156 0.34
## Number of obs: 4395, groups: site_name, 20
##
## Conditional model:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.300797 0.556971 -2.335 0.01952 *
## SMA_RGFA1 0.500736 0.024646 20.317 < 2e-16 ***
## SMA_RGFA2 0.182341 0.033653 5.418 6.02e-08 ***
## SMA_RGFA3 0.209126 0.025445 8.219 < 2e-16 ***
## SMA_RGFA4 -0.174227 0.026173 -6.657 2.80e-11 ***
## SMA_RGFA5 -0.014301 0.029327 -0.488 0.62582
## SMA_RGFA6 -0.007878 0.026359 -0.299 0.76504
## SMA_RGFA7 0.014081 0.027977 0.503 0.61475
## SMA_RGFA8 -0.024542 0.032412 -0.757 0.44894
## age -0.001893 0.004067 -0.466 0.64157
## femaleyes -0.120460 0.064354 -1.872 0.06123 .
## race.ethnicityBlack -0.355091 0.116719 -3.042 0.00235 **
## race.ethnicityHispanic -0.510717 0.105045 -4.862 1.16e-06 ***
## race.ethnicityAsian 0.813728 0.158090 5.147 2.64e-07 ***
## race.ethnicityOther -0.087106 0.099255 -0.878 0.38016
## high.educHS Degree 0.298566 0.210386 1.419 0.15586
## high.educCollege Degree 0.497560 0.218590 2.276 0.02283 *
## high.educBachelor 0.584017 0.216650 2.696 0.00702 **
## high.educHigher 0.533431 0.222081 2.402 0.01631 *
## high.educ_miss 0.873833 0.749378 1.166 0.24358
## marriedyes -0.126554 0.072868 -1.737 0.08243 .
## HHInc[50K - 100K] -0.037590 0.089456 -0.420 0.67433
## HHInc[>100K] 0.036737 0.099917 0.368 0.71312
## HHInc_miss -0.309998 0.137875 -2.248 0.02455 *
## demo_prnt_age_v2 -0.006001 0.004834 -1.241 0.21444
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot_model(kidsi_sma_nZIP,type="est",vline.color = "red",order.terms = c(1:24),show.values = TRUE,value.offset = .75,title = "nZIP Screen Media GFA: Total Youth Suicide Items, no zero inflation")

# Compare the AIC
bictab <- BICtab(kidsi_cov_ZIP,
kidsi_sma_ZIP,
kidsi_cov_pZIP,
kidsi_sma_pZIP,
kidsi_cov_ZINB,
kidsi_sma_ZINB,
kidsi_sma_pZINB,
kidsi_sma_nZIP,
kidsi_sma_nZINB,logLik=TRUE,base=TRUE)
tabAsStringMatrix <- print(bictab, printToggle = FALSE, noSpaces = TRUE)
## logLik BIC dLogLik dBIC df
## kidsi_sma_nZINB -2423.0 5072.5 684.0 0.0 27
## kidsi_sma_ZINB -2423.0 5080.9 684.0 8.4 28
## kidsi_cov_ZINB -2498.7 5165.2 608.3 92.7 20
## kidsi_sma_ZIP -2564.8 5356.2 542.1 283.7 27
## kidsi_cov_ZIP -2628.9 5417.1 478.1 344.7 19
## kidsi_sma_pZIP -2491.5 5419.1 615.5 346.6 52
## kidsi_sma_pZINB -2491.5 5419.1 615.5 346.6 52
## kidsi_cov_pZIP -2605.2 5512.4 501.8 439.9 36
## kidsi_sma_nZIP -3107.0 6432.0 0.0 1359.6 26
kable(tabAsStringMatrix, "html",caption = "Bayesian Information Criterion: Model Comparison") %>% kable_styling(bootstrap_options = c( "hover", "condensed", "responsive"),font_size = 11)
Bayesian Information Criterion: Model Comparison
|
|
logLik
|
BIC
|
dLogLik
|
dBIC
|
df
|
|
kidsi_sma_nZINB
|
-2423.0
|
5072.5
|
684.0
|
0.0
|
27
|
|
kidsi_sma_ZINB
|
-2423.0
|
5080.9
|
684.0
|
8.4
|
28
|
|
kidsi_cov_ZINB
|
-2498.7
|
5165.2
|
608.3
|
92.7
|
20
|
|
kidsi_sma_ZIP
|
-2564.8
|
5356.2
|
542.1
|
283.7
|
27
|
|
kidsi_cov_ZIP
|
-2628.9
|
5417.1
|
478.1
|
344.7
|
19
|
|
kidsi_sma_pZIP
|
-2491.5
|
5419.1
|
615.5
|
346.6
|
52
|
|
kidsi_sma_pZINB
|
-2491.5
|
5419.1
|
615.5
|
346.6
|
52
|
|
kidsi_cov_pZIP
|
-2605.2
|
5512.4
|
501.8
|
439.9
|
36
|
|
kidsi_sma_nZIP
|
-3107.0
|
6432.0
|
0.0
|
1359.6
|
26
|
# Plotting Results
# Remove high variance variables:
myremove <- c(1,20)
# Forming different data frames for each model:
dfmymodel <- createCoeftab(kidsi_sma_ZINB,"ZINB, standard zero inflation",c(GFAselectLabel,colabels),myremove)
dfmymodel2 <- createCoeftab(kidsi_sma_pZINB,"ZINB, parameterized zero inflation",c(GFAselectLabel,colabels),myremove)
dfmymodel3 <- createCoeftab(kidsi_sma_ZIP,"ZIP, standard zero inflation",c(GFAselectLabel,colabels),myremove)
dfmymodel4 <- createCoeftab(kidsi_sma_nZINB,"ZINB, no zero inflation",c(GFAselectLabel,colabels),myremove)
allmodels <- rbind(dfmymodel,dfmymodel2,dfmymodel3,dfmymodel4)
# Plotting all models
ggplot(allmodels, aes(x = estimate, y = term, colour = model, shape = model, xmax = upper, xmin = lower)) + theme_minimal() +
geom_vline(xintercept = 0, colour = "grey60", linetype = 2) +
geom_pointrangeh(position = position_dodgev(height = 0.5)) +
labs(y = NULL,
x = "Regression estimate +/- CI",
title = "Zero Inflated Models")

# Exponentiated Model
ggplot(allmodels, aes(x = expestimate, y = term, colour = model, shape = model, xmax = expupper, xmin = explower)) + theme_minimal() +
geom_vline(xintercept = 1, colour = "grey60", linetype = 2) +
geom_pointrangeh(position = position_dodgev(height = 0.5)) +
labs(y = NULL,
x = "Risk Ratio estimates +/- CI",
title = "Zero Inflated Models")

# Plot best model
ggplot(dfmymodel4, aes(x = estimate, y = term, xmax = upper, xmin = lower)) + theme_minimal() +
geom_vline(xintercept = 0, colour = "grey60", linetype = 2) +
geom_text(aes(label = format(estimate, digits=2, nsmall=2)),nudge_y = -0.3,nudge_x = 0.3,size = 3) +
geom_pointrangeh(position = position_dodgev(height = 0.5)) +
labs(y = NULL,
x = "Regression estimate +/- CI",
title = "Best Non-Zero Inflated Model: Negative Binomial")

# Interpretation: https://stats.idre.ucla.edu/stata/output/negative-binomial-regression/
# http://fmwww.bc.edu/ec-c/s2013/327/S5CountCategorical0511.slides.pdf
# for a one unit change in the predictor variable, the difference in the logs of expected counts of the response variable is expected to change by the respective regression coefficient, given the other predictor variables in the model are held constant
# Exponentiated Model
ggplot(dfmymodel4, aes(x = expestimate, y = term, xmax = expupper, xmin = explower)) + theme_minimal() +
geom_vline(xintercept = 1, colour = "grey60", linetype = 2) +
geom_text(aes(label = format(expestimate, digits=2, nsmall=2)),nudge_y = -0.3,nudge_x = 0.3,size = 3) +
geom_pointrangeh(position = position_dodgev(height = 0.5)) +
labs(y = NULL,
x = "Risk Ratio estimates +/- CI",
title = "Best Non-Zero Inflated Model: Negative Binomial")

# Interpretation: http://www.mathematica-journal.com/2013/06/negative-binomial-regression/
# Incidence Rate Ratio (IRR) for each variable, which is obtained by exponentiating each coefficient
# Plot a grid of effects:
theme_set(theme_sjplot())
plotlist <- list()
depvars <- paste0("SMA_RGFA",rep(1:4))
# Arrange the marginal plots in a grid of 4 without scatter plots:
for(i in 1:length(depvars)){
p1 <- plot_model(kidsi_sma_nZINB,type = "pred",terms = c(depvars[i],"female"),title = "",axis.title = c(GFAselectLabel[i],"Youth Total SI Items"))
plotlist[[i]] <- p1
}
## Following variables had many unique values and were prettified: SMA_RGFA1. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
## Following variables had many unique values and were prettified: SMA_RGFA2. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
## Following variables had many unique values and were prettified: SMA_RGFA3. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
## Following variables had many unique values and were prettified: SMA_RGFA4. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
mygridtitle <- paste("Marginal Plots: ",sep="")
grid.arrange(plotlist[[1]],plotlist[[2]],plotlist[[3]],plotlist[[4]],ncol = 2,top=mygridtitle)

# Arrange the marginal plots in a grid of 4 with scatter plots:
for(i in 1:length(depvars)){
p1 <- plot_model(kidsi_sma_nZINB,type = "pred",terms = c(depvars[i],"female"),title = "",axis.title = c(GFAselectLabel[i],"Youth Total SI Items"),show.data = TRUE)
plotlist[[i]] <- p1
}
## Following variables had many unique values and were prettified: SMA_RGFA1. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
## Following variables had many unique values and were prettified: SMA_RGFA2. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
## Following variables had many unique values and were prettified: SMA_RGFA3. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
## Following variables had many unique values and were prettified: SMA_RGFA4. Use `pretty = FALSE` to get smoother plots with all values, however, at the cost of increased memory usage.
mygridtitle <- paste("Marginal Plots: ",sep="")
grid.arrange(plotlist[[1]],plotlist[[2]],plotlist[[3]],plotlist[[4]],ncol = 2,top=mygridtitle)

This is the logistic regression with both site and family as a random effect. Although there is an output and reasonable stastistics, the routine threw a warning about possible convergence problems.
# Set up the variables:
covars <- c("age","female","race.ethnicity","high.educ","married","HHInc","demo_prnt_age_v2")
colabels <- c("Age","Female","Race: Black","Race: Hispanic","Race: Asian","Race: Other","Parental Education: HS","Parental Education: College","Parental Education: Bachelor","Parental Education: > Bachelor","Parental Education: missing","Married","Household Income: 50-100K","Household Income: > 100K","Household Income: miss","Parental Age")
## Select the nesting variables: site and twin status
nestvars <- c("site_name","FamilyID")
# Independent variables:
indepvars <- paste0("SMA_RGFA",rep(1:8))
# dependent variables:
depvars <- c("KidsSIyes","ParSIyes")
GFAselectLabel <- paste0("SMA_RGFA",rep(1:8))
# Creating a data frame:
glmmadmbdata <- currdata[complete.cases(currdata[,c(covars,nestvars,depvars,indepvars)]),c(covars,nestvars,depvars,indepvars)]
# Visualizing missing data
aggr(currdata[,c(covars,nestvars,depvars,indepvars)],col = c("blue","orange"),sortVars=TRUE,prop = FALSE, numbers = TRUE, combined = TRUE, cex.lab = 0.5, cex.axis =0.5, cex.numbers =0.5)

##
## Variables sorted by number of missings:
## Variable Count
## ParSIyes 70
## KidsSIyes 53
## demo_prnt_age_v2 43
## race.ethnicity 2
## age 0
## female 0
## high.educ 0
## married 0
## HHInc 0
## site_name 0
## FamilyID 0
## SMA_RGFA1 0
## SMA_RGFA2 0
## SMA_RGFA3 0
## SMA_RGFA4 0
## SMA_RGFA5 0
## SMA_RGFA6 0
## SMA_RGFA7 0
## SMA_RGFA8 0
mydepvar <- c("KidsSIyes")
# Compare the model with and without the GFAs:
mygamm4base <- myGAMM4Bin(mydepvar,"null",covars,nestvars,glmmadmbdata)
mygamm4GFA <- myGAMM4Bin(mydepvar,indepvars,covars,nestvars,glmmadmbdata)
# Summary of logistic regression
summary(mygamm4base$mer)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
##
## AIC BIC logLik deviance df.resid
## 2783.7 2905.1 -1372.9 2745.7 4376
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.8201 -0.0125 -0.0043 -0.0009 5.8822
##
## Random effects:
## Groups Name Variance Std.Dev.
## FamilyID:site_name (Intercept) 1.724e+02 13.130199
## site_name (Intercept) 2.125e-06 0.001458
## Number of obs: 4395, groups: FamilyID:site_name, 3816; site_name, 20
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## X(Intercept) -29.26396 5.97755 -4.896 9.80e-07 ***
## Xage 0.21379 0.03727 5.737 9.66e-09 ***
## Xfemaleyes -1.40832 0.65128 -2.162 0.030587 *
## Xrace.ethnicityBlack -8.87263 2.28436 -3.884 0.000103 ***
## Xrace.ethnicityHispanic -2.49010 1.44891 -1.719 0.085688 .
## Xrace.ethnicityAsian 0.17799 3.28808 0.054 0.956830
## Xrace.ethnicityOther 2.55967 1.29133 1.982 0.047456 *
## Xhigh.educHS Degree -2.19768 2.59444 -0.847 0.396953
## Xhigh.educCollege Degree -1.18882 2.81928 -0.422 0.673261
## Xhigh.educBachelor -0.86491 2.74201 -0.315 0.752435
## Xhigh.educHigher -0.66527 2.80094 -0.238 0.812257
## Xhigh.educ_miss 4.26981 9.68121 0.441 0.659183
## Xmarriedyes -0.39745 1.24628 -0.319 0.749794
## XHHInc[50K - 100K] -3.00808 1.49577 -2.011 0.044320 *
## XHHInc[>100K] -3.32062 1.58725 -2.092 0.036433 *
## XHHInc_miss -3.96844 2.33582 -1.699 0.089328 .
## Xdemo_prnt_age_v2 -0.03457 0.08096 -0.427 0.669324
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation matrix not shown by default, as p = 17 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it
## convergence code: 0
## failure to converge in 10000 evaluations
##
## Family: binomial
## Link function: logit
##
## Formula:
## KidsSIyes ~ age + female + race.ethnicity + high.educ + married +
## HHInc + demo_prnt_age_v2
## <environment: 0x7fd543f3bc38>
##
## Parametric coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -29.26396 5.97755 -4.896 9.80e-07 ***
## age 0.21379 0.03727 5.737 9.66e-09 ***
## femaleyes -1.40832 0.65128 -2.162 0.030587 *
## race.ethnicityBlack -8.87263 2.28436 -3.884 0.000103 ***
## race.ethnicityHispanic -2.49010 1.44891 -1.719 0.085688 .
## race.ethnicityAsian 0.17799 3.28808 0.054 0.956830
## race.ethnicityOther 2.55967 1.29133 1.982 0.047456 *
## high.educHS Degree -2.19768 2.59444 -0.847 0.396953
## high.educCollege Degree -1.18882 2.81928 -0.422 0.673261
## high.educBachelor -0.86491 2.74201 -0.315 0.752435
## high.educHigher -0.66527 2.80094 -0.238 0.812257
## high.educ_miss 4.26981 9.68121 0.441 0.659183
## marriedyes -0.39745 1.24628 -0.319 0.749794
## HHInc[50K - 100K] -3.00808 1.49577 -2.011 0.044320 *
## HHInc[>100K] -3.32062 1.58725 -2.092 0.036433 *
## HHInc_miss -3.96844 2.33582 -1.699 0.089328 .
## demo_prnt_age_v2 -0.03457 0.08096 -0.427 0.669324
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## R-sq.(adj) = -0.00425
## glmer.ML = 419.44 Scale est. = 1 n = 4395
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
##
## AIC BIC logLik deviance df.resid
## 3268.2 3440.7 -1607.1 3214.2 4368
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.4291 -0.3682 -0.2990 -0.2355 4.7467
##
## Random effects:
## Groups Name Variance Std.Dev.
## FamilyID:site_name (Intercept) 0.58233 0.7631
## site_name (Intercept) 0.05495 0.2344
## Number of obs: 4395, groups: FamilyID:site_name, 3816; site_name, 20
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## X(Intercept) -0.230776 1.017997 -0.227 0.820660
## XSMA_RGFA1 0.590580 0.088840 6.648 2.98e-11 ***
## XSMA_RGFA2 0.121004 0.059190 2.044 0.040922 *
## XSMA_RGFA3 0.170115 0.051041 3.333 0.000859 ***
## XSMA_RGFA4 -0.148340 0.053008 -2.798 0.005135 **
## XSMA_RGFA5 0.002801 0.051022 0.055 0.956218
## XSMA_RGFA6 -0.017267 0.049750 -0.347 0.728529
## XSMA_RGFA7 0.018334 0.051260 0.358 0.720595
## XSMA_RGFA8 0.013130 0.057281 0.229 0.818697
## Xage -0.014486 0.006919 -2.094 0.036287 *
## Xfemaleyes -0.226142 0.111591 -2.027 0.042711 *
## Xrace.ethnicityBlack -0.371209 0.251975 -1.473 0.140698
## Xrace.ethnicityHispanic -0.250511 0.172323 -1.454 0.146022
## Xrace.ethnicityAsian 0.415554 0.322224 1.290 0.197175
## Xrace.ethnicityOther 0.143342 0.175433 0.817 0.413883
## Xhigh.educHS Degree 0.118232 0.317668 0.372 0.709753
## Xhigh.educCollege Degree 0.222132 0.334909 0.663 0.507164
## Xhigh.educBachelor 0.285381 0.333071 0.857 0.391547
## Xhigh.educHigher 0.331531 0.344813 0.961 0.336310
## Xhigh.educ_miss 0.415166 1.401604 0.296 0.767072
## Xmarriedyes -0.068178 0.129646 -0.526 0.598975
## XHHInc[50K - 100K] 0.174714 0.158230 1.104 0.269516
## XHHInc[>100K] 0.278856 0.185834 1.501 0.133469
## XHHInc_miss -0.014378 0.222728 -0.065 0.948530
## Xdemo_prnt_age_v2 -0.011587 0.008313 -1.394 0.163399
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation matrix not shown by default, as p = 25 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it
## convergence code: 0
## failure to converge in 10000 evaluations
##
## Family: binomial
## Link function: logit
##
## Formula:
## KidsSIyes ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 + SMA_RGFA5 +
## SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female + race.ethnicity +
## high.educ + married + HHInc + demo_prnt_age_v2
## <environment: 0x7fd529ac4ff0>
##
## Parametric coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.230776 0.915068 -0.252 0.800890
## SMA_RGFA1 0.590580 0.048544 12.166 < 2e-16 ***
## SMA_RGFA2 0.121004 0.056579 2.139 0.032462 *
## SMA_RGFA3 0.170115 0.048760 3.489 0.000485 ***
## SMA_RGFA4 -0.148340 0.049693 -2.985 0.002835 **
## SMA_RGFA5 0.002801 0.049283 0.057 0.954674
## SMA_RGFA6 -0.017267 0.047178 -0.366 0.714363
## SMA_RGFA7 0.018334 0.050364 0.364 0.715836
## SMA_RGFA8 0.013130 0.056663 0.232 0.816754
## age -0.014486 0.006885 -2.104 0.035395 *
## femaleyes -0.226142 0.107885 -2.096 0.036069 *
## race.ethnicityBlack -0.371209 0.204715 -1.813 0.069786 .
## race.ethnicityHispanic -0.250511 0.158790 -1.578 0.114654
## race.ethnicityAsian 0.415554 0.315391 1.318 0.187643
## race.ethnicityOther 0.143342 0.165558 0.866 0.386593
## high.educHS Degree 0.118232 0.309955 0.381 0.702869
## high.educCollege Degree 0.222132 0.328777 0.676 0.499275
## high.educBachelor 0.285381 0.323032 0.883 0.376997
## high.educHigher 0.331531 0.331524 1.000 0.317300
## high.educ_miss 0.415166 1.361234 0.305 0.760372
## marriedyes -0.068178 0.126371 -0.540 0.589539
## HHInc[50K - 100K] 0.174714 0.157043 1.113 0.265913
## HHInc[>100K] 0.278856 0.173978 1.603 0.108974
## HHInc_miss -0.014378 0.222246 -0.065 0.948419
## demo_prnt_age_v2 -0.011587 0.008254 -1.404 0.160374
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## R-sq.(adj) = 0.0453
## glmer.ML = 2698.3 Scale est. = 1 n = 4395
# Visualize the GAMM4 Coefficients:
# https://cran.r-project.org/web/packages/merTools/vignettes/merToolsIntro.html
feEx <- FEsim(mygamm4GFA$mer,1000)
cbind(feEx[,1],round(feEx[,2:4],3))
## feEx[, 1] mean median sd
## 1 X(Intercept) -0.256 -0.295 0.902
## 2 XSMA_RGFA1 0.593 0.592 0.051
## 3 XSMA_RGFA2 0.121 0.120 0.057
## 4 XSMA_RGFA3 0.170 0.169 0.049
## 5 XSMA_RGFA4 -0.149 -0.148 0.048
## 6 XSMA_RGFA5 0.003 0.002 0.049
## 7 XSMA_RGFA6 -0.021 -0.023 0.048
## 8 XSMA_RGFA7 0.019 0.020 0.049
## 9 XSMA_RGFA8 0.012 0.011 0.058
## 10 Xage -0.015 -0.015 0.007
## 11 Xfemaleyes -0.225 -0.226 0.109
## 12 Xrace.ethnicityBlack -0.371 -0.374 0.209
## 13 Xrace.ethnicityHispanic -0.250 -0.253 0.156
## 14 Xrace.ethnicityAsian 0.425 0.428 0.306
## 15 Xrace.ethnicityOther 0.141 0.139 0.166
## 16 Xhigh.educHS Degree 0.132 0.134 0.317
## 17 Xhigh.educCollege Degree 0.250 0.260 0.327
## 18 Xhigh.educBachelor 0.309 0.312 0.329
## 19 Xhigh.educHigher 0.352 0.367 0.344
## 20 Xhigh.educ_miss 0.440 0.490 1.376
## 21 Xmarriedyes -0.068 -0.069 0.127
## 22 XHHInc[50K - 100K] 0.171 0.175 0.156
## 23 XHHInc[>100K] 0.274 0.275 0.178
## 24 XHHInc_miss -0.020 -0.013 0.216
## 25 Xdemo_prnt_age_v2 -0.011 -0.012 0.008
feEx$term <- c("Intercept",indepvars,colabels)
feEx$term <- factor(feEx$term,levels = c("Intercept",indepvars,colabels))
# reeduce the data for plotting:
reddata <- feEx[feEx$term!= "Intercept" & feEx$term!= "Parental Education: missing", ]
reddata <- droplevels(reddata)
# theme_bw() +
gamm4coeff <- ggplot(reddata) +
theme_minimal() +
aes(x = term, ymin = median - 1.96 * sd,
ymax = median + 1.96 * sd, y = median) +
geom_pointrange() +
scale_x_discrete(limits = rev(levels(reddata$term))) +
geom_text(aes(label = sprintf("%0.2f", round(median, digits = 2))),
position=position_dodge(width=0.9), vjust=-0.75) +
geom_hline(yintercept = 0, size = I(1.1), color = I("red")) +
coord_flip() +
labs(title = paste("Kids SI Logistic Regression",": Median Effect Size",sep=""),
x = "Variables", y = "Standardized Coefficients")
print(gamm4coeff)

ExpfeEx <- data.frame(exp(feEx$mean),exp(feEx$median),exp(feEx$median-1.96*feEx$sd),exp(feEx$median+1.96*feEx$sd))
ExpfeEx <- data.frame(cbind(feEx$term,ExpfeEx))
colnames(ExpfeEx) <- c("term","mean","median","Lower_CI","Upper_CI")
ExpfeEx$term = factor(ExpfeEx$term,levels = c("Intercept",indepvars,colabels))
reddata <- ExpfeEx[ExpfeEx$term!= "Intercept" & ExpfeEx$term!= "Parental Education: missing", ]
reddata <- droplevels(reddata)
# theme_bw() +
# Exponentiated Results:
gamm4coeff <- ggplot(reddata) +
theme_minimal() +
aes(x = term, ymin = Lower_CI,
ymax = Upper_CI, y = median) +
geom_pointrange() +
scale_x_discrete(limits = rev(levels(reddata$term))) +
geom_text(aes(label = sprintf("%0.2f", round(median, digits = 2))),
position=position_dodge(width=0.9), vjust=-0.75) +
geom_hline(yintercept = 1, size = I(1.1), color = I("red")) +
coord_flip() +
labs(title = paste("Kids Sucidal Ideation",": Odds Ratios",sep=""),
x = "Variables", y = "Risk Ratio estimates +/- CI")
print(gamm4coeff)

This is the logistic Regression with site only as the random effect because there were some convergence problems when including both site and family as a random effect.
# Set up the variables:
covars <- c("age","female","race.ethnicity","high.educ","married","HHInc","demo_prnt_age_v2")
colabels <- c("Age","Female","Race: Black","Race: Hispanic","Race: Asian","Race: Other","Parental Education: HS","Parental Education: College","Parental Education: Bachelor","Parental Education: > Bachelor","Parental Education: missing","Married","Household Income: 50-100K","Household Income: > 100K","Household Income: miss","Parental Age")
## Select the nesting variables: site and twin status
nestvars <- c("site_name")
# Independent variables:
indepvars <- paste0("SMA_RGFA",rep(1:8))
# dependent variables:
depvars <- c("KidsSIyes","ParSIyes")
GFAselectLabel <- paste0("SMA_RGFA",rep(1:8))
# Creating a data frame:
glmmadmbdata <- currdata[complete.cases(currdata[,c(covars,nestvars,depvars,indepvars)]),c(covars,nestvars,depvars,indepvars)]
# Visualizing missing data
aggr(currdata[,c(covars,nestvars,depvars,indepvars)],col = c("blue","orange"),sortVars=TRUE,prop = FALSE, numbers = TRUE, combined = TRUE, cex.lab = 0.5, cex.axis =0.5, cex.numbers =0.5)

##
## Variables sorted by number of missings:
## Variable Count
## ParSIyes 70
## KidsSIyes 53
## demo_prnt_age_v2 43
## race.ethnicity 2
## age 0
## female 0
## high.educ 0
## married 0
## HHInc 0
## site_name 0
## SMA_RGFA1 0
## SMA_RGFA2 0
## SMA_RGFA3 0
## SMA_RGFA4 0
## SMA_RGFA5 0
## SMA_RGFA6 0
## SMA_RGFA7 0
## SMA_RGFA8 0
mydepvar <- c("KidsSIyes")
# Compare the model with and without the GFAs:
mygamm4base <- myGAMM4Bin(mydepvar,"null",covars,nestvars,glmmadmbdata)
mygamm4GFA <- myGAMM4Bin(mydepvar,indepvars,covars,nestvars,glmmadmbdata)
# Summary of logistic regression
summary(mygamm4base$mer)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
##
## AIC BIC logLik deviance df.resid
## 3420.8 3535.8 -1692.4 3384.8 4377
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.6661 -0.4180 -0.3647 -0.3125 3.9438
##
## Random effects:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.05065 0.225
## Number of obs: 4395, groups: site_name, 20
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## X(Intercept) 0.469804 0.822880 0.571 0.5680
## Xage -0.014858 0.006229 -2.385 0.0171 *
## Xfemaleyes -0.427060 0.091935 -4.645 3.4e-06 ***
## Xrace.ethnicityBlack -0.306963 0.180590 -1.700 0.0892 .
## Xrace.ethnicityHispanic -0.279086 0.145618 -1.917 0.0553 .
## Xrace.ethnicityAsian 0.257080 0.286187 0.898 0.3690
## Xrace.ethnicityOther 0.194162 0.148827 1.305 0.1920
## Xhigh.educHS Degree 0.178690 0.285970 0.625 0.5321
## Xhigh.educCollege Degree 0.266027 0.302290 0.880 0.3788
## Xhigh.educBachelor 0.249574 0.296579 0.842 0.4001
## Xhigh.educHigher 0.234990 0.302710 0.776 0.4376
## Xhigh.educ_miss 1.087923 1.202850 0.904 0.3658
## Xmarriedyes -0.187883 0.113537 -1.655 0.0980 .
## XHHInc[50K - 100K] 0.048831 0.141481 0.345 0.7300
## XHHInc[>100K] 0.073596 0.156544 0.470 0.6383
## XHHInc_miss -0.062693 0.199541 -0.314 0.7534
## Xdemo_prnt_age_v2 -0.012234 0.007516 -1.628 0.1036
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation matrix not shown by default, as p = 17 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it
##
## Family: binomial
## Link function: logit
##
## Formula:
## KidsSIyes ~ age + female + race.ethnicity + high.educ + married +
## HHInc + demo_prnt_age_v2
## <environment: 0x7fd53e7147c8>
##
## Parametric coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.469804 0.824131 0.570 0.5686
## age -0.014858 0.006237 -2.382 0.0172 *
## femaleyes -0.427060 0.092044 -4.640 3.49e-06 ***
## race.ethnicityBlack -0.306963 0.180731 -1.698 0.0894 .
## race.ethnicityHispanic -0.279086 0.145085 -1.924 0.0544 .
## race.ethnicityAsian 0.257080 0.286354 0.898 0.3693
## race.ethnicityOther 0.194162 0.148971 1.303 0.1925
## high.educHS Degree 0.178690 0.286485 0.624 0.5328
## high.educCollege Degree 0.266027 0.302858 0.878 0.3797
## high.educBachelor 0.249574 0.297047 0.840 0.4008
## high.educHigher 0.234990 0.303001 0.776 0.4380
## high.educ_miss 1.087923 1.202303 0.905 0.3655
## marriedyes -0.187883 0.113661 -1.653 0.0983 .
## HHInc[50K - 100K] 0.048831 0.141698 0.345 0.7304
## HHInc[>100K] 0.073596 0.156758 0.469 0.6387
## HHInc_miss -0.062693 0.199888 -0.314 0.7538
## demo_prnt_age_v2 -0.012234 0.007528 -1.625 0.1042
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## R-sq.(adj) = 0.00727
## glmer.ML = 3358.5 Scale est. = 1 n = 4395
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
##
## AIC BIC logLik deviance df.resid
## 3270.5 3436.6 -1609.3 3218.5 4369
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.5863 -0.4034 -0.3267 -0.2551 5.6666
##
## Random effects:
## Groups Name Variance Std.Dev.
## site_name (Intercept) 0.08448 0.2907
## Number of obs: 4395, groups: site_name, 20
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## X(Intercept) -0.105069 0.859948 -0.122 0.902756
## XSMA_RGFA1 0.551162 0.045478 12.119 < 2e-16 ***
## XSMA_RGFA2 0.126897 0.052923 2.398 0.016495 *
## XSMA_RGFA3 0.173123 0.045319 3.820 0.000133 ***
## XSMA_RGFA4 -0.139466 0.046120 -3.024 0.002495 **
## XSMA_RGFA5 0.006997 0.046122 0.152 0.879416
## XSMA_RGFA6 -0.009551 0.044447 -0.215 0.829864
## XSMA_RGFA7 0.019842 0.047163 0.421 0.673969
## XSMA_RGFA8 0.015024 0.052976 0.284 0.776725
## Xage -0.015173 0.006445 -2.354 0.018568 *
## Xfemaleyes -0.208093 0.100198 -2.077 0.037818 *
## Xrace.ethnicityBlack -0.340183 0.190411 -1.787 0.074007 .
## Xrace.ethnicityHispanic -0.218884 0.150043 -1.459 0.144618
## Xrace.ethnicityAsian 0.432521 0.290193 1.490 0.136104
## Xrace.ethnicityOther 0.114887 0.154229 0.745 0.456325
## Xhigh.educHS Degree 0.212306 0.296457 0.716 0.473903
## Xhigh.educCollege Degree 0.320058 0.313358 1.021 0.307074
## Xhigh.educBachelor 0.388491 0.308335 1.260 0.207682
## Xhigh.educHigher 0.438993 0.316224 1.388 0.165066
## Xhigh.educ_miss 0.711396 1.215506 0.585 0.558368
## Xmarriedyes -0.057951 0.117264 -0.494 0.621168
## XHHInc[50K - 100K] 0.167292 0.146085 1.145 0.252137
## XHHInc[>100K] 0.251290 0.162283 1.548 0.121510
## XHHInc_miss 0.004942 0.206253 0.024 0.980885
## Xdemo_prnt_age_v2 -0.010365 0.007687 -1.348 0.177543
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation matrix not shown by default, as p = 25 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it
##
## Family: binomial
## Link function: logit
##
## Formula:
## KidsSIyes ~ SMA_RGFA1 + SMA_RGFA2 + SMA_RGFA3 + SMA_RGFA4 + SMA_RGFA5 +
## SMA_RGFA6 + SMA_RGFA7 + SMA_RGFA8 + age + female + race.ethnicity +
## high.educ + married + HHInc + demo_prnt_age_v2
## <environment: 0x7fd5325bec00>
##
## Parametric coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.105069 0.860465 -0.122 0.902814
## SMA_RGFA1 0.551162 0.045238 12.184 < 2e-16 ***
## SMA_RGFA2 0.126897 0.053001 2.394 0.016655 *
## SMA_RGFA3 0.173123 0.045270 3.824 0.000131 ***
## SMA_RGFA4 -0.139466 0.046141 -3.023 0.002506 **
## SMA_RGFA5 0.006997 0.046175 0.152 0.879552
## SMA_RGFA6 -0.009551 0.044460 -0.215 0.829911
## SMA_RGFA7 0.019842 0.047195 0.420 0.674177
## SMA_RGFA8 0.015024 0.053037 0.283 0.776972
## age -0.015173 0.006449 -2.353 0.018638 *
## femaleyes -0.208093 0.100368 -2.073 0.038144 *
## race.ethnicityBlack -0.340183 0.190262 -1.788 0.073780 .
## race.ethnicityHispanic -0.218884 0.150034 -1.459 0.144593
## race.ethnicityAsian 0.432521 0.290535 1.489 0.136565
## race.ethnicityOther 0.114887 0.154395 0.744 0.456809
## high.educHS Degree 0.212306 0.296981 0.715 0.474684
## high.educCollege Degree 0.320058 0.313900 1.020 0.307910
## high.educBachelor 0.388491 0.308789 1.258 0.208352
## high.educHigher 0.438993 0.316621 1.386 0.165596
## high.educ_miss 0.711396 1.214148 0.586 0.557928
## marriedyes -0.057951 0.117424 -0.494 0.621644
## HHInc[50K - 100K] 0.167292 0.146307 1.143 0.252857
## HHInc[>100K] 0.251290 0.162452 1.547 0.121897
## HHInc_miss 0.004942 0.206620 0.024 0.980919
## demo_prnt_age_v2 -0.010365 0.007697 -1.347 0.178111
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## R-sq.(adj) = 0.046
## glmer.ML = 3184.8 Scale est. = 1 n = 4395
# Visualize the GAMM4 Coefficients:
# https://cran.r-project.org/web/packages/merTools/vignettes/merToolsIntro.html
feEx <- FEsim(mygamm4GFA$mer,1000)
cbind(feEx[,1],round(feEx[,2:4],3))
## feEx[, 1] mean median sd
## 1 X(Intercept) -0.101 -0.105 0.814
## 2 XSMA_RGFA1 0.555 0.556 0.046
## 3 XSMA_RGFA2 0.128 0.129 0.051
## 4 XSMA_RGFA3 0.173 0.174 0.045
## 5 XSMA_RGFA4 -0.138 -0.137 0.046
## 6 XSMA_RGFA5 0.005 0.006 0.046
## 7 XSMA_RGFA6 -0.009 -0.010 0.046
## 8 XSMA_RGFA7 0.021 0.021 0.046
## 9 XSMA_RGFA8 0.014 0.016 0.055
## 10 Xage -0.015 -0.015 0.006
## 11 Xfemaleyes -0.215 -0.213 0.098
## 12 Xrace.ethnicityBlack -0.349 -0.350 0.195
## 13 Xrace.ethnicityHispanic -0.226 -0.223 0.147
## 14 Xrace.ethnicityAsian 0.423 0.413 0.283
## 15 Xrace.ethnicityOther 0.118 0.113 0.155
## 16 Xhigh.educHS Degree 0.214 0.211 0.289
## 17 Xhigh.educCollege Degree 0.317 0.312 0.302
## 18 Xhigh.educBachelor 0.391 0.398 0.304
## 19 Xhigh.educHigher 0.441 0.446 0.316
## 20 Xhigh.educ_miss 0.747 0.739 1.239
## 21 Xmarriedyes -0.053 -0.053 0.116
## 22 XHHInc[50K - 100K] 0.159 0.162 0.146
## 23 XHHInc[>100K] 0.239 0.236 0.164
## 24 XHHInc_miss 0.011 0.013 0.203
## 25 Xdemo_prnt_age_v2 -0.010 -0.010 0.007
feEx$term <- c("Intercept",indepvars,colabels)
feEx$term <- factor(feEx$term,levels = c("Intercept",indepvars,colabels))
# reeduce the data for plotting:
reddata <- feEx[feEx$term!= "Intercept" & feEx$term!= "Parental Education: missing", ]
reddata <- droplevels(reddata)
# theme_bw() +
gamm4coeff <- ggplot(reddata) +
theme_minimal() +
aes(x = term, ymin = median - 1.96 * sd,
ymax = median + 1.96 * sd, y = median) +
geom_pointrange() +
scale_x_discrete(limits = rev(levels(reddata$term))) +
geom_text(aes(label = sprintf("%0.2f", round(median, digits = 2))),
position=position_dodge(width=0.9), vjust=-0.75) +
geom_hline(yintercept = 0, size = I(1.1), color = I("red")) +
coord_flip() +
labs(title = paste("Kids SI Logistic Regression",": Median Effect Size",sep=""),
x = "Variables", y = "Standardized Coefficients")
print(gamm4coeff)

ExpfeEx <- data.frame(exp(feEx$mean),exp(feEx$median),exp(feEx$median-1.96*feEx$sd),exp(feEx$median+1.96*feEx$sd))
ExpfeEx <- data.frame(cbind(feEx$term,ExpfeEx))
colnames(ExpfeEx) <- c("term","mean","median","Lower_CI","Upper_CI")
ExpfeEx$term = factor(ExpfeEx$term,levels = c("Intercept",indepvars,colabels))
reddata <- ExpfeEx[ExpfeEx$term!= "Intercept" & ExpfeEx$term!= "Parental Education: missing", ]
reddata <- droplevels(reddata)
# theme_bw() +
# Exponentiated Results:
gamm4coeff <- ggplot(reddata) +
theme_minimal() +
aes(x = term, ymin = Lower_CI,
ymax = Upper_CI, y = median) +
geom_pointrange() +
scale_x_discrete(limits = rev(levels(reddata$term))) +
geom_text(aes(label = sprintf("%0.2f", round(median, digits = 2))),
position=position_dodge(width=0.9), vjust=-0.75) +
geom_hline(yintercept = 1, size = I(1.1), color = I("red")) +
coord_flip() +
labs(title = paste("Kids Sucidal Ideation",": Odds Ratios",sep=""),
x = "Variables", y = "Risk Ratio estimates +/- CI")
print(gamm4coeff)

These are bar plots of the SMA variables by GFA standard deviations
# This is based on tabledata, which was generated by the standard deviation variable
# of the GFAs
# Pick the color based on: https://htmlcolorcodes.com/color-picker/
tabledata <- currdata[,c(mysdGFA,listvars)]
tablenames <- names(tabledata)
mysmas <- tablenames[grep("_y_",tablenames)]
mysmalabels <- c("Watching TV/Movies per week [h]","Watching Videos per week [h]","Playing Games per week [h]","Texting per week [h]","Social Networking per week [h]","Chatting per week [h]")
for (i in 1:8){
p <- list()
for (j in 1: length(mysmas)){
myplotGFA <- paste0("sdGFA",i)
completetabledata <- tabledata[complete.cases(tabledata[,c(myplotGFA)]),]
p[[j]] <-ggplot(data=completetabledata, aes_string(x=myplotGFA, y=mysmas[j])) +
geom_bar(stat = "summary", fun.y = "mean",fill="#FF3396") + coord_flip() +
# ggtitle("Media Activity and GFA") +
ylim(0, 22) +
stat_summary(aes(label=round(..y..,2)), fun.y=mean, geom="text", size=3,
color = "black",hjust=-0.1) +
xlab(paste0("GFA",i)) + ylab(mysmalabels[j]) + theme_minimal()
# print(p[[i]])
}
do.call("grid.arrange", c(p,list(ncol=2, top=textGrob(paste0("GFA ",i)))))
# do.call(grid.arrange,c(p,main="text"))
}
## Warning: Removed 397 rows containing non-finite values (stat_summary).
## Warning: Removed 397 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 353 rows containing non-finite values (stat_summary).
## Warning: Removed 353 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 342 rows containing non-finite values (stat_summary).
## Warning: Removed 342 rows containing non-finite values (stat_summary).
## Warning: Removed 358 rows containing non-finite values (stat_summary).
## Warning: Removed 358 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 374 rows containing non-finite values (stat_summary).
## Warning: Removed 374 rows containing non-finite values (stat_summary).
## Warning: Removed 307 rows containing non-finite values (stat_summary).
## Warning: Removed 307 rows containing non-finite values (stat_summary).
## Warning: Removed 327 rows containing non-finite values (stat_summary).
## Warning: Removed 327 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 6 rows containing non-finite values (stat_summary).
## Warning: Removed 6 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).

## Warning: Removed 354 rows containing non-finite values (stat_summary).
## Warning: Removed 354 rows containing non-finite values (stat_summary).
## Warning: Removed 292 rows containing non-finite values (stat_summary).
## Warning: Removed 292 rows containing non-finite values (stat_summary).
## Warning: Removed 297 rows containing non-finite values (stat_summary).
## Warning: Removed 297 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).
## Warning: Removed 8 rows containing non-finite values (stat_summary).
## Warning: Removed 8 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).

## Warning: Removed 401 rows containing non-finite values (stat_summary).
## Warning: Removed 401 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 355 rows containing non-finite values (stat_summary).
## Warning: Removed 355 rows containing non-finite values (stat_summary).
## Warning: Removed 46 rows containing non-finite values (stat_summary).
## Warning: Removed 46 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 36 rows containing non-finite values (stat_summary).
## Warning: Removed 36 rows containing non-finite values (stat_summary).

## Warning: Removed 391 rows containing non-finite values (stat_summary).
## Warning: Removed 391 rows containing non-finite values (stat_summary).
## Warning: Removed 337 rows containing non-finite values (stat_summary).
## Warning: Removed 337 rows containing non-finite values (stat_summary).
## Warning: Removed 352 rows containing non-finite values (stat_summary).
## Warning: Removed 352 rows containing non-finite values (stat_summary).
## Warning: Removed 45 rows containing non-finite values (stat_summary).
## Warning: Removed 45 rows containing non-finite values (stat_summary).
## Warning: Removed 20 rows containing non-finite values (stat_summary).
## Warning: Removed 20 rows containing non-finite values (stat_summary).
## Warning: Removed 34 rows containing non-finite values (stat_summary).
## Warning: Removed 34 rows containing non-finite values (stat_summary).

## Warning: Removed 399 rows containing non-finite values (stat_summary).
## Warning: Removed 399 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 352 rows containing non-finite values (stat_summary).
## Warning: Removed 352 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 389 rows containing non-finite values (stat_summary).
## Warning: Removed 389 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 356 rows containing non-finite values (stat_summary).
## Warning: Removed 356 rows containing non-finite values (stat_summary).
## Warning: Removed 44 rows containing non-finite values (stat_summary).
## Warning: Removed 44 rows containing non-finite values (stat_summary).
## Warning: Removed 21 rows containing non-finite values (stat_summary).
## Warning: Removed 21 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

for (j in 1: length(mysmas)){
p <- list()
for (i in 1:4){
myplotGFA <- paste0("sdGFA",i)
completetabledata <- tabledata[complete.cases(tabledata[,c(myplotGFA)]),]
p[[i]] <-ggplot(data=completetabledata, aes_string(x=myplotGFA, y=mysmas[j])) +
geom_bar(stat = "summary", fun.y = "mean",fill="skyblue") + coord_flip() +
# ggtitle("Media Activity and GFA") +
ylim(0, 22) +
stat_summary(aes(label=round(..y..,2)), fun.y=mean, geom="text", size=3,
color = "black",hjust=-0.1) +
xlab(paste0("GFA",i)) + ylab(mysmalabels[j]) + theme_minimal()
# print(p[[i]])
}
do.call("grid.arrange", c(p,list(ncol=2, top=textGrob(paste0("GFA Groups and ",mysmalabels[j])))))
# do.call(grid.arrange,p)
}
## Warning: Removed 397 rows containing non-finite values (stat_summary).
## Warning: Removed 397 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 374 rows containing non-finite values (stat_summary).
## Warning: Removed 374 rows containing non-finite values (stat_summary).
## Warning: Removed 354 rows containing non-finite values (stat_summary).
## Warning: Removed 354 rows containing non-finite values (stat_summary).

## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 339 rows containing non-finite values (stat_summary).
## Warning: Removed 342 rows containing non-finite values (stat_summary).
## Warning: Removed 342 rows containing non-finite values (stat_summary).
## Warning: Removed 307 rows containing non-finite values (stat_summary).
## Warning: Removed 307 rows containing non-finite values (stat_summary).
## Warning: Removed 292 rows containing non-finite values (stat_summary).
## Warning: Removed 292 rows containing non-finite values (stat_summary).

## Warning: Removed 353 rows containing non-finite values (stat_summary).
## Warning: Removed 353 rows containing non-finite values (stat_summary).
## Warning: Removed 358 rows containing non-finite values (stat_summary).
## Warning: Removed 358 rows containing non-finite values (stat_summary).
## Warning: Removed 327 rows containing non-finite values (stat_summary).
## Warning: Removed 327 rows containing non-finite values (stat_summary).
## Warning: Removed 297 rows containing non-finite values (stat_summary).
## Warning: Removed 297 rows containing non-finite values (stat_summary).

## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).

## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 6 rows containing non-finite values (stat_summary).
## Warning: Removed 6 rows containing non-finite values (stat_summary).
## Warning: Removed 8 rows containing non-finite values (stat_summary).
## Warning: Removed 8 rows containing non-finite values (stat_summary).

## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 16 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).
## Warning: Removed 27 rows containing non-finite values (stat_summary).

These are barplots by GFA of the SMA by quartiles.
# This is based on tabledata, which was generated by the standard deviation variable
# of the GFAs
# Pick the color based on: https://htmlcolorcodes.com/color-picker/
tabledata <- currdata[,c(myqGFA,listvars)]
tablenames <- names(tabledata)
mysmas <- tablenames[grep("_y_",tablenames)]
mysmalabels <- c("Watching TV/Movies per week [h]","Watching Videos per week [h]","Playing Games per week [h]","Texting per week [h]","Social Networking per week [h]","Chatting per week [h]")
for (i in 1:8){
p <- list()
for (j in 1: length(mysmas)){
myplotGFA <- paste0("qGFA",i)
completetabledata <- tabledata[complete.cases(tabledata[,c(myplotGFA)]),]
p[[j]] <-ggplot(data=completetabledata, aes_string(x=myplotGFA, y=mysmas[j])) +
geom_bar(stat = "summary", fun.y = "mean",fill="#FF3396") + coord_flip() +
# ggtitle("Media Activity and GFA") +
ylim(0, 22) +
stat_summary(aes(label=round(..y..,2)), fun.y=mean, geom="text", size=3,
color = "black",hjust=-0.1) +
xlab(paste0("GFA",i)) + ylab(mysmalabels[j]) + theme_minimal()
# print(p[[i]])
}
do.call("grid.arrange", c(p,list(ncol=2, top=textGrob(paste0("GFA ",i)))))
# do.call(grid.arrange,c(p,main="text"))
}
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).

for (j in 1: length(mysmas)){
p <- list()
for (i in 1:4){
myplotGFA <- paste0("qGFA",i)
completetabledata <- tabledata[complete.cases(tabledata[,c(myplotGFA)]),]
p[[i]] <-ggplot(data=completetabledata, aes_string(x=myplotGFA, y=mysmas[j])) +
geom_bar(stat = "summary", fun.y = "mean",fill="skyblue") + coord_flip() +
# ggtitle("Media Activity and GFA") +
ylim(0, 22) +
stat_summary(aes(label=round(..y..,2)), fun.y=mean, geom="text", size=3,
color = "black",hjust=-0.1) +
xlab(paste0("GFA",i)) + ylab(mysmalabels[j]) + theme_minimal()
# print(p[[i]])
}
do.call("grid.arrange", c(p,list(ncol=2, top=textGrob(paste0("GFA Quartiles and ",mysmalabels[j])))))
# do.call(grid.arrange,p)
}
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).
## Warning: Removed 403 rows containing non-finite values (stat_summary).

## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).
## Warning: Removed 343 rows containing non-finite values (stat_summary).

## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).
## Warning: Removed 359 rows containing non-finite values (stat_summary).

## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).
## Warning: Removed 47 rows containing non-finite values (stat_summary).

## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).
## Warning: Removed 22 rows containing non-finite values (stat_summary).

## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
## Warning: Removed 37 rows containing non-finite values (stat_summary).
